Use cases › Capability
Chat and follow instructions
Instruction-tuned assistants for conversation, writing, Q&A and following formatting rules.
Benchmarks that represent this job 14
A model's row on one of these third-party boards is what earns the measured label; the same benchmark name in the model's own card earns author-reported.
IFEvalIFBenchArena-HardAlpacaEvalMT-BenchWildBenchMulti-IFCreative WritingHellaSwagTruthfulQAWinograndeARC ChallengeMultiChallengeCommonsense QA sets
Models 464
Narrow by what you can run and pay for. Rows are ordered measured → author-reported → structural, then by watch-list score; click a column to re-sort. Every chip links to its source.
| Model | Evidence | Params | Context | Price from | Runs on | License | Providers | Measured latency |
|---|---|---|---|---|---|---|---|---|
| DeepSeek-V4.1-Flash deepseek-ai | author-reported Author reports HellaSwag (EM) 87.2decision-model estimate p=0.81 +1 | 763B | 1M | $0.02 | Cluster | MIT | 8 | — |
| Qwen3.5-9B Qwen | author-reported Author reports IFEval 91.5Author reports IFBench 64.5 +1 | 9.65B | 256K | $0.08 | Single GPU | Apache 2.0 | 6 | 2.8 s · 117 tok/s |
| DeepSeek-V4-Pro deepseek-ai | author-reported Author reports TriviaQA (EM) 85.6Author reports HellaSwag (EM) 88.0 +1 | 1.60T | 1M | $0.21 | Cluster | MIT | 5 | — |
| DeepSeek-R1 deepseek-ai | author-reported Author reports IF-Eval (Prompt Strict) 83.3Author reports AlpacaEval2.0 (LC-winrate) 87.6 +1 | 684B | 160K | $0.70 | Cluster | MIT | 3 | — |
| Qwen3.5-397B-A17B Qwen | author-reported Author reports IFEval 92.6Author reports IFBench 76.5 +1 | 403B (17B active) | 256K | $0.39 | Cluster | Apache 2.0 | 7 | — |
| DeepSeek-V4-Flash deepseek-ai | author-reported Author reports TriviaQA (EM) 82.8Author reports HellaSwag (EM) 85.7 +1 | 291B | 1M | $0.03 | Cluster | MIT | 4 | — |
| gemma-3-4b-it google | author-reported Author reports HellaSwag 77.2Author reports ARC-e 82.4 +1 | 4.30B | 128K | $0.04 | Single GPU | Gemma Terms of Use attribution | 4 | — |
| Qwen3.5-35B-A3B Qwen | author-reported Author reports IFEval 91.9Author reports IFBench 70.2 +1 | 36.0B (3B active) | 256K | $0.07 | Multi-GPU node | Apache 2.0 | 4 | — |
| gemma-3-27b-it google | author-reported Author reports HellaSwag 85.6Author reports ARC-e 89.0 +1 | 27.4B | 128K | $0.08 | Single high-end GPU | Gemma Terms of Use attribution | 4 | — |
| Qwen3.5-27B Qwen | author-reported Author reports IFEval 95.0Author reports IFBench 76.5 +1 | 27.8B | 256K | $0.20 | Single high-end GPU | Apache 2.0 | 4 | — |
| Qwen3.5-4B Qwen | author-reported Author reports IFEval 89.8Author reports IFBench 59.2 +1 | 4.66B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| DeepSeek-V3 deepseek-ai | author-reported Author reports ARC-Easy (Acc.) 98.9Author reports ARC-Challenge (Acc.) 95.3 +1 | 684B | 160K | $0.26 | Cluster | Not declared review | 2 | — |
| Qwen3-Next-80B-A3B-Instruct Qwen | author-reported Author reports IFEval 87.6Author reports Arena-Hard v2* 82.7 +1 | 81.3B (3B active) | 256K | $0.07 | Multi-GPU node | Apache 2.0 | 4 | — |
| gemma-3-12b-it google | author-reported Author reports HellaSwag 84.2Author reports ARC-e 88.3 +1 | 12.2B | 128K | $0.04 | Single high-end GPU | Gemma Terms of Use attribution | 3 | — |
| Qwen3-4B-Instruct-2507 Qwen | author-reported Author reports IFEval 83.4Author reports Arena-Hard v2* 43.4 +1 | 4.02B | 256K | $0.01 | Single GPU | Apache 2.0 | 1 | — |
| gemma-3-1b-it google | author-reported Author reports HellaSwag 62.3Author reports PIQA 73.8 +1 | 1000M | 32K | — | Laptop / edge | Gemma Terms of Use attribution | 1 | — |
| Qwen3-235B-A22B-Instruct-2507 Qwen | author-reported Author reports IFEval 88.7Author reports Arena-Hard v2* 79.2 +1 | 235B (22B active) | 256K | $0.09 | Multi-GPU node | Apache 2.0 | 5 | — |
| Qwen3-30B-A3B-Instruct-2507 Qwen | author-reported Author reports IFEval 84.7Author reports Arena-Hard v2* 69.0 +1 | 30.5B (3B active) | 256K | $0.09 | Single high-end GPU | Apache 2.0 | 2 | — |
| Qwen3.5-122B-A10B Qwen | author-reported Author reports IFEval 93.4Author reports IFBench 76.1 +1 | 125B (10B active) | 256K | $0.26 | Multi-GPU node | Apache 2.0 | 3 | — |
| Muse-Glimmer-30B meta-models | author-reported Author reports IFBench 77.0decision-model estimate p=0.75 +1 | 29.8B | 128K | $0.30 | Single high-end GPU | Apache 2.0 | 4 | — |
| Qwen2-7B-Instruct Qwen | author-reported Author reports MT-Bench 8.41decision-model estimate p=1.00 +1 | 7.62B | 32K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen3.5-2B Qwen | author-reported Author reports IFEval 78.6Author reports IFBench 41.3 +1 | 2.27B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen3-4B-Thinking-2507 Qwen | author-reported Author reports IFEval 87.4Author reports Arena-Hard v2$ 34.9 +1 | 4.02B | 256K | $0.01 | Single GPU | Apache 2.0 | 2 | — |
| Qwen3.5-0.8B Qwen | author-reported Author reports IFEval 52.1Author reports IFBench 21.0 +1 | 873M | 256K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Inkling thinkingmachines | author-reported Author reports IFBench 79.8%decision-model estimate p=0.99 +1 | 952B | 1M | $0.00 | Cluster | Apache 2.0 | 4 | — |
| gemma-2-2b google | author-reported Author reports HellaSwag 73.0Author reports ARC-e 80.1 +1 | 2.61B | 8K | — | Single GPU | Gemma Terms of Use attribution | 1 | — |
| gemma-3-270m google | author-reported Author reports HellaSwag 40.9Author reports PIQA 67.7 +1 | 268M | 32K | — | Laptop / edge | Gemma Terms of Use attribution | 0 | — |
| Phi-4-mini-instruct microsoft | author-reported Author reports Arena Hard 32.8Author reports ARC Challenge (10-shot) 83.7 +1 | 3.84B | 128K | — | Single GPU | MIT | 0 | — |
| zephyr-7b-beta HuggingFaceH4 | author-reported Author reports MT-Bench (score) 7.34Author reports AlpacaEval (win rate %) 90.60 +1 | 7.24B | 32K | — | Single GPU | MIT | 1 | — |
| SmolLM2-135M HuggingFaceTB | author-reported Author reports HellaSwag 42.1Author reports PIQA 68.4 +1 | 135M | 8K | — | Laptop / edge | Apache 2.0 | 0 | — |
| gpt-j-6b EleutherAI | author-reported Author reports Winogrande ↑ 65.3%Author reports Hellaswag ↑ 66.1% +1 | — | 2K | — | — | Apache 2.0 | 0 | — |
| Hermes-3-Llama-3.1-8B NousResearch | author-reported Author reports IFEval (0-Shot) 61.70decision-model estimate p=1.00 +1 | 8.03B | 128K | — | Single GPU | Llama 3 Community License attribution | 1 | — |
| SmolLM3-3B HuggingFaceTB | author-reported Author reports IFEval 76.7Author reports HellaSwag 76.15 +1 | 3.08B | 64K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen2-72B-Instruct Qwen | author-reported Author reports MT-Bench 9.12Author reports Arena-Hard 48.1 +1 | 72.7B | 32K | — | Multi-GPU node | tongyi-qianwen review | 2 | — |
| Apertus-8B-Instruct-2509 swiss-ai | author-reported Author reports ARC 72.7Author reports HellaSwag 64.0 +1 | 8.05B | 64K | $0.10 | Single GPU | Apache 2.0 | 2 | — |
| Qwen2-1.5B-Instruct Qwen | author-reported Author reports IFEval (Prompt Strict-Acc.) 29.0decision-model estimate p=1.00 +1 | 1.54B | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| NVIDIA-Nemotron-Nano-9B-v2 nvidia | author-reported Author reports IFEval (Instruction Strict) 90.3%decision-model estimate p=0.98 +1 | 8.89B | 128K | — | Single GPU | NVIDIA Open Model License… attribution | 1 | — |
| Qwen3-235B-A22B-Thinking-2507 Qwen | author-reported Author reports IFEval 87.8Author reports Arena-Hard v2$ 79.7 +1 | 235B (22B active) | 256K | $0.23 | Multi-GPU node | Apache 2.0 | 3 | — |
| gemma-2-9b google | author-reported Author reports HellaSwag 81.9Author reports ARC-e 88.0 +1 | 9.24B | 8K | — | Single GPU | Gemma Terms of Use attribution | 1 | — |
| gemma-3-270m-it google | author-reported Author reports HellaSwag 40.9Author reports PIQA 67.7 +1 | 268M | 32K | — | Laptop / edge | Gemma Terms of Use attribution | 0 | — |
| Qwen3-30B-A3B-Thinking-2507 Qwen | author-reported Author reports IFEval 88.9Author reports Arena-Hard v2$ 56.0 +1 | 30.5B (3B active) | 256K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Qwen2-0.5B-Instruct Qwen | author-reported Author reports IFEval (Prompt Strict-Acc.) 20.0decision-model estimate p=1.00 +1 | 494M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen2-0.5B Qwen | author-reported Author reports HellaSwag 49.3Author reports Winogrande 56.8 +1 | 494M | 128K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Llama-3.1-Nemotron-70B-Instruct-HF nvidia | author-reported Author reports Arena Hard 85.0Author reports MT-Bench 8.98 +1 | 70.6B | 128K | — | Multi-GPU node | Llama 3.1 Community Licen… attribution | 1 | — |
| Qwen3-Next-80B-A3B-Thinking Qwen | author-reported Author reports IFEval 88.9Author reports Arena-Hard v2* 62.3 +1 | 81.3B (3B active) | 256K | $0.15 | Multi-GPU node | Apache 2.0 | 1 | — |
| gpt-neox-20b EleutherAI | author-reported Author reports PIQA 0.779 ± 0.010Author reports ARC (Challenge) 0.380 ± 0.014 +1 | 20.7B | 2K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| gemma-3-4b-pt google | author-reported Author reports HellaSwag 77.2Author reports ARC-e 82.4 +1 | 4.30B | — | — | Single GPU | Gemma Terms of Use attribution | 1 | — |
| gpt-neo-125m EleutherAI | author-reported Author reports HellaSwag (10-shot) 30.26Author reports TruthfulQA (0-shot) 45.58 +1 | 150M | 2K | — | Laptop / edge | MIT | 0 | — |
| gemma-3n-E2B-it google | author-reported Author reports HellaSwag 72.2Author reports PIQA 78.9 +1 | 5.44B | 32K | — | Single GPU | Gemma Terms of Use attribution | 0 | — |
| Phi-3.5-MoE-instruct microsoft | author-reported Author reports Arena Hard 37.9Author reports ARC Challenge (10-shot) 91.0 +1 | 41.9B | 128K | — | Multi-GPU node | MIT | 0 | — |
| gpt-neo-2.7B EleutherAI | author-reported Author reports Winogrande 56.50%Author reports Hellaswag 42.73% +1 | 2.72B | 2K | — | Single GPU | MIT | 0 | — |
| DeepSeek-V4-Flash-DSpark deepseek-ai | author-reported Author reports TriviaQA (EM) 82.8Author reports HellaSwag (EM) 85.7 +1 | 165B | 1M | — | Multi-GPU node | MIT | 0 | — |
| MiMo-V2.5-Pro XiaomiMiMo | author-reported Author reports ARC-Challenge 97.2Author reports HellaSwag 89.8 +1 | 1.02T | 1M | $0.30 | Cluster | MIT | 2 | — |
| OpenHermes-2.5-Mistral-7B teknium | author-reported Author reports TruthfulQA 53.04Author reports arc_challenge 0.5623 +1 | 7.24B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2-7B Qwen | author-reported Author reports HellaSwag 80.7Author reports Winogrande 77.0 +1 | 7.62B | 128K | — | Single GPU | Apache 2.0 | 1 | — |
| gemma-3n-E4B-it google | author-reported Author reports HellaSwag 78.6Author reports BoolQ 81.6 +1 | 7.85B | 32K | — | Single GPU | Gemma Terms of Use attribution | 0 | — |
| gemma-3-1b-pt google | author-reported Author reports HellaSwag 62.3Author reports PIQA 73.8 +1 | 1000M | 32K | — | Laptop / edge | Gemma Terms of Use attribution | 1 | — |
| gpt-neo-1.3B EleutherAI | author-reported Author reports Winogrande (5-shot) 56.91Author reports HellaSwag (10-shot) 48.47 +1 | 1.37B | 2K | — | Laptop / edge | MIT | 0 | — |
| granite-4.1-8b ibm-granite | author-reported Author reports AlpacaEval 2.0 50.08Author reports IFEval Avg 87.06 +1 | 8.79B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen2-1.5B Qwen | author-reported Author reports HellaSwag 66.6Author reports Winogrande 66.2 +1 | 1.54B | 128K | — | Laptop / edge | Apache 2.0 | 1 | — |
| bitnet-b1.58-2B-4T microsoft | author-reported Author reports ARC-Challenge 49.91Author reports BoolQ 80.18 +1 | 850M | 4K | — | Laptop / edge | MIT | 0 | — |
| DialoGPT-small microsoft | author-reported Author reports HellaSwag (10-shot) 25.79Author reports TruthfulQA (0-shot) 47.49 +1 | 176M | 1K | — | Laptop / edge | MIT | 0 | — |
| granite-4.1-3b ibm-granite | author-reported Author reports AlpacaEval 2.0 38.57Author reports IFEval Avg 82.30 +1 | 3.40B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| EXAONE-3.5-7.8B-Instruct LGAI-EXAONE | author-reported Author reports MT-Bench 8.29Author reports Arena-Hard 68.7 +1 | 7.82B | 32K | — | Single GPU | exaone review | 0 | — |
| openchat_3.5 openchat | author-reported Author reports MT-Bench 7.81Author reports TruthfulQA 59.1 +1 | — | 8K | — | — | Apache 2.0 | 2 | — |
| Olmo-3-7B-Instruct allenai | author-reported Author reports IFEval 85.6Author reports IFBench 27.4 +1 | 7.30B | 64K | — | Single GPU | Apache 2.0 | 0 | — |
| gemma-3-12b-pt google | author-reported Author reports HellaSwag 84.2Author reports ARC-e 88.3 +1 | 12.2B | — | — | Single high-end GPU | Gemma Terms of Use attribution | 1 | — |
| Llama-2-7b-hf NousResearch | author-reported Author reports TruthfulQA 57.04 | 6.74B | 4K | — | Single GPU | Not declared review | 1 | — |
| Jamba-v0.1 ai21labs | author-reported Author reports HellaSwag 87.1%Author reports Arc Challenge 64.4% +1 | 51.6B | 256K | — | Multi-GPU node | Apache 2.0 | 0 | — |
| Llama-3.1-Nemotron-Nano-8B-v1 nvidia | author-reported Author reports MT-Bench 8.1Author reports IFEval Average 82.1% +1 | 8.03B | 128K | — | Single GPU | NVIDIA Open Model License… attribution | 1 | — |
| Meta-Llama-3.1-8B-Instruct NousResearch | author-reported Author reports TriviaQA-Wiki 77.6Author reports Winogrande 60.5 +1 | 8.03B | 128K | — | Single GPU | Llama 3.1 Community Licen… attribution | 1 | — |
| t5gemma-2-270m-270m google | author-reported Author reports HellaSwag 41.1Author reports PIQA 66.5 +1 | 786M | — | — | Laptop / edge | Gemma Terms of Use attribution | 0 | — |
| MiMo-V2-Flash XiaomiMiMo | author-reported Author reports ARC-Challenge 95.9Author reports HellaSwag 88.5 +1 | 310B | 256K | — | Cluster | MIT | 0 | — |
| Nanbeige4.2-3B Nanbeige | author-reported Author reports IF-Bench 54.6decision-model estimate p=0.84 +1 | 4.17B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| LFM2-1.2B LiquidAI | author-reported Author reports IFEval 74.89Author reports IFBench 20.7 +1 | 1.17B | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| LFM2.5-VL-450M LiquidAI | author-reported Author reports MM-IFEval 45.00decision-model estimate p=0.95 +1 | 449M | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| gemma-3n-E2B-it-litert-lm google | author-reported Author reports HellaSwag 72.2Author reports PIQA 78.9 +1 | — | — | — | — | Gemma Terms of Use attribution | 0 | — |
| DeepSeek-V2.5 deepseek-ai | author-reported Author reports AlpacaEval 2.0 50.5Author reports ArenaHard 76.2 +1 | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen2-72B Qwen | author-reported Author reports HellaSwag 87.6Author reports ARC-C 68.9 +1 | 72.7B | 128K | — | Multi-GPU node | tongyi-qianwen review | 1 | — |
| Kimi-K3-DSpark RadixArk | author-reported Author reports MT-Bench 3.9342 | 2.25B | 1M | — | Single GPU | Not declared review | 0 | — |
| Llama-3_3-Nemotron-Super-49B-v1 nvidia | author-reported Author reports Arena-Hard 88.3decision-model estimate p=1.00 +1 | 49.9B | 128K | — | Multi-GPU node | NVIDIA Open Model License… attribution | 0 | — |
| Moonlight-16B-A3B-Instruct moonshotai | author-reported Author reports TriviaQA‡ 66.3decision-model estimate p=1.00 +1 | 16.0B (3B active) | 8K | — | Single high-end GPU | MIT | 0 | — |
| gemma-2-27b google | author-reported Author reports HellaSwag 86.4Author reports ARC-e 88.6 +1 | 27.2B | 8K | $0.65 | Single high-end GPU | Gemma Terms of Use attribution | 1 | — |
| Nemotron-Cascade-2-30B-A3B nvidia | author-reported Author reports ArenaHard v2 (Avg.) 83.5Author reports IFBench (prompt) 82.9 +1 | 31.6B (3B active) | 256K | — | Single high-end GPU | NVIDIA Open Model License… attribution | 0 | — |
| granite-4.0-h-tiny ibm-granite | author-reported Author reports AlpacaEval 2.0 30.61Author reports IFEval 84.78 +1 | 6.94B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| OpenELM-1_1B-Instruct apple | author-reported Author reports ARC-c 41.55Author reports PIQA 75.03 +1 | 1.08B | — | — | Laptop / edge | apple-sample-code-license review | 0 | — |
| Llama-2-7b-chat-hf NousResearch | author-reported Author reports TruthfulQA 57.04decision-model estimate p=1.00 +1 | 6.74B | 4K | — | Single GPU | Not declared review | 1 | — |
| Nanbeige4.1-3B Nanbeige | author-reported Author reports Arena-Hard-v2 73.2Author reports Multi-Challenge 52.21 +1 | 3.93B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| SmolLM2-360M HuggingFaceTB | author-reported Author reports HellaSwag 54.5Author reports PIQA 71.7 +1 | 362M | 8K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Olmo-3-7B-Think allenai | author-reported Author reports IFEval 77.9tag: conversational +1 | 7.30B | 64K | — | Single GPU | Apache 2.0 | 0 | — |
| LFM2.5-VL-1.6B LiquidAI | author-reported Author reports MM-IFEval 52.29decision-model estimate p=0.89 +1 | 1.60B | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| internlm3-8b-instruct internlm | author-reported Author reports HellaSwag(10-shot) 91.2Author reports IFEval(Prompt-Strict) 79.3 +1 | 8.80B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| Hy3-preview tencent | author-reported Author reports ARC-Challenge 95.99Author reports PIQA 84.39 +1 | 299B | 256K | $0.18 | Cluster | Other review | 1 | — |
| granite-4.0-h-small ibm-granite | author-reported Author reports AlpacaEval 2.0 42.48Author reports IFEval 89.87 +1 | 32.2B | 128K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| EXAONE-3.5-2.4B-Instruct LGAI-EXAONE | author-reported Author reports MT-Bench 7.81Author reports Arena-Hard 48.2 +1 | 2.41B | 32K | — | Single GPU | exaone review | 0 | — |
| gemma-3n-E4B-it-litert-lm google | author-reported Author reports HellaSwag 78.6Author reports BoolQ 81.6 +1 | — | — | — | — | Gemma Terms of Use attribution | 0 | — |
| OLMoE-1B-7B-0924 allenai | author-reported Author reports HellaSwag 80.0Author reports ARC-Chall. 62.1 +1 | 6.92B | 4K | — | Single GPU | Apache 2.0 | 0 | — |
| K-EXAONE-236B-A23B LGAI-EXAONE | author-reported Author reports IFBench 67.3Author reports IFEval 89.7 +1 | 237B (23B active) | 256K | — | Multi-GPU node | k-exaone review | 0 | — |
| saiga_llama3_8b IlyaGusev | author-reported Author reports alpaca_eval_cot_gpt4_turbo_fn 69.40decision-model estimate p=1.00 +1 | 8.03B | 8K | — | Single GPU | Llama Community License (… attribution | 1 | — |
| Llama-2-13b-hf NousResearch | author-reported Author reports TruthfulQA 62.18 | 13.0B | 4K | — | Single high-end GPU | Not declared review | 1 | — |
| Phi-tiny-MoE-instruct microsoft | author-reported Author reports Arc-C (chat) 76.37Author reports MT-bench 7.05 +1 | 3.76B | 4K | — | Single GPU | MIT | 0 | — |
| pplx-decider-v1-27b perplexity-ai | author-reported Author reports WinoGrande 83.30%Author reports TruthfulQA binary 85.40% +1 | 26.1B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| jpt-4b kirp | author-reported Author reports Language HellaSwag 74.7Author reports Language WinoGrande 42.5 +1 | 4.54B | 256K | — | Single GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| metask-jev-4b-policy-mix wayfind | author-reported Author reports boolq 87.3%chat template present | 4.54B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| jpt-9b kirp | author-reported Author reports HellaSwag 81.2Author reports WinoGrande 49.2 +1 | 9.41B | 256K | — | Single GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| Qwen3.8-27B Qwen | structural decision-model estimate p=0.99tag: conversational +1 | 27.8B | 256K | $0.02 | Single high-end GPU | Apache 2.0 | 7 | 28.6 s · 87 tok/s |
| gpt-oss-120b openai | structural decision-model estimate p=0.99tag: conversational +1 | 117B | 128K | $0.03 | Multi-GPU node | Apache 2.0 | 13 | 0.8 s · 168 tok/s |
| GLM-5.3-Flash zai-org | structural decision-model estimate p=0.99tag: conversational +1 | 321B | 1M | $0.02 | Cluster | MIT | 9 | 8.1 s · 153 tok/s |
| gpt-oss-20b openai | structural decision-model estimate p=0.93tag: conversational +1 | 20.9B | 128K | $0.02 | Single high-end GPU | Apache 2.0 | 7 | 2.8 s · 58 tok/s |
| gemma-4-26B-A4B-it google | structural decision-model estimate p=1.00name: it +1 | 25.8B (4B active) | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 6 | 0.9 s · 51 tok/s |
| GLM-5.3 zai-org | structural decision-model estimate p=0.98tag: conversational +1 | 753B | 1M | $0.07 | Cluster | GLM License (glm-5.3) review | 9 | — |
| Kimi-K3 moonshotai | structural decision-model estimate p=0.97tag: conversational | 2.78T | 1M | $0.23 | Cluster | Kimi K3 (Modified MIT) (k… gated-threshold | 7 | 25.6 s · 59 tok/s |
| gemma-4-31B-it google | structural decision-model estimate p=1.00name: it +1 | 31.3B | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 5 | — |
| GLM-5.2 zai-org | structural decision-model estimate p=0.96tag: conversational +1 | 753B | 1M | $0.03 | Cluster | MIT | 9 | — |
| Llama-3.1-8B-Instruct meta-llama | structural decision-model estimate p=0.99name: Instruct +1 | 8.03B | 128K | $0.02 | Single GPU | Llama 3.1 Community Licen… attribution | 4 | — |
| Llama-3.3-70B-Instruct meta-llama | structural decision-model estimate p=1.00name: Instruct +1 | 70.6B | 128K | $0.10 | Multi-GPU node | Llama 3.3 Community Licen… attribution | 7 | — |
| Qwen3.6-35B-A3B Qwen | structural decision-model estimate p=0.98tag: conversational +1 | 36.0B (3B active) | 256K | $0.05 | Multi-GPU node | Apache 2.0 | 5 | — |
| Llama-3.2-3B-Instruct meta-llama | structural decision-model estimate p=1.00name: Instruct +1 | 3.21B | 128K | $0.05 | Single GPU | Llama 3.2 Community Licen… attribution | 4 | — |
| GLM-4.7-Flash zai-org | structural decision-model estimate p=0.99tag: conversational +1 | 31.2B | 198K | $0.06 | Single high-end GPU | MIT | 5 | — |
| Qwen3-VL-8B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 8.77B | 256K | $0.25 | Single GPU | Apache 2.0 | 4 | — |
| Qwen3-8B Qwen | structural decision-model estimate p=0.92tag: conversational +1 | 8.19B | 40K | $0.07 | Single GPU | Apache 2.0 | 3 | — |
| Qwen2.5-7B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 7.62B | 32K | $0.10 | Single GPU | Apache 2.0 | 3 | — |
| MiniMax-M3 MiniMaxAI | structural decision-model estimate p=0.97tag: conversational +1 | 427B | 1M | $0.22 | Cluster | MiniMax Model License (mi… gated-threshold | 7 | — |
| Llama-3.2-1B-Instruct meta-llama | structural decision-model estimate p=0.99name: Instruct +1 | 1.24B | 59K | $0.03 | Laptop / edge | Llama 3.2 Community Licen… attribution | 3 | — |
| Kimi-K2.6 moonshotai | structural decision-model estimate p=0.93tag: conversational +1 | 1.03T | 256K | $0.45 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 5 | — |
| Qwen3-14B Qwen | structural decision-model estimate p=0.77tag: conversational +1 | 14.8B | 40K | $0.07 | Single high-end GPU | Apache 2.0 | 4 | — |
| Qwen3-0.6B Qwen | structural decision-model estimate p=0.81tag: conversational +1 | 752M | 40K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen3-32B Qwen | structural decision-model estimate p=0.97tag: conversational +1 | 32.8B | 40K | $0.08 | Single high-end GPU | Apache 2.0 | 4 | — |
| Qwen3.6-27B Qwen | structural decision-model estimate p=0.97tag: conversational +1 | 27.8B | 256K | $0.20 | Single high-end GPU | Apache 2.0 | 4 | — |
| Kimi-K2.5 moonshotai | structural decision-model estimate p=0.96tag: conversational +1 | 1.03T | 256K | $0.45 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| Qwen2.5-Coder-32B-Instruct Qwen | structural decision-model estimate p=0.99name: Instruct +1 | 32.8B | 32K | $0.06 | Single high-end GPU | Apache 2.0 | 4 | — |
| GLM-5 zai-org | structural decision-model estimate p=0.93tag: conversational +1 | 754B | 198K | $0.60 | Cluster | MIT | 5 | — |
| Qwen3.8-Flash-Next Qwen | structural decision-model estimate p=0.96tag: conversational +1 | 180B | 256K | $0.15 | Multi-GPU node | Qwen License (qwen-commun… gated-threshold | 2 | — |
| Meta-Llama-3-8B-Instruct meta-llama | structural decision-model estimate p=0.99name: Instruct +1 | 8.03B | — | — | Single GPU | Llama 3 Community License attribution | 2 | — |
| DeepSeek-R1-0528 deepseek-ai | structural decision-model estimate p=0.99tag: conversational +1 | 685B | 160K | $0.50 | Cluster | MIT | 4 | — |
| MiniMax-M2.5 MiniMaxAI | structural decision-model estimate p=0.89tag: conversational +1 | 229B | 192K | $0.27 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 4 | — |
| Qwen3-235B-A22B Qwen | structural decision-model estimate p=0.96tag: conversational +1 | 235B (22B active) | 40K | $0.20 | Multi-GPU node | Apache 2.0 | 4 | — |
| Qwen3-Coder-30B-A3B-Instruct Qwen | structural decision-model estimate p=0.92name: Instruct +1 | 30.5B (3B active) | 256K | $0.07 | Single high-end GPU | Apache 2.0 | 3 | — |
| Qwen2.5-1.5B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 1.54B | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen3-VL-30B-A3B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 31.1B (3B active) | 256K | $0.15 | Single high-end GPU | Apache 2.0 | 4 | — |
| Qwen3-Embedding-0.6B Qwen | structural chat template present | 596M | 32K | $0.01 | Laptop / edge | Apache 2.0 | 1 | — |
| gemma-4-E4B-it google | structural decision-model estimate p=1.00name: it +1 | 8.00B | 128K | — | Single GPU | Apache 2.0 | 1 | — |
| GLM-5.1 zai-org | structural decision-model estimate p=0.94tag: conversational +1 | 754B | 198K | $0.96 | Cluster | MIT | 4 | — |
| Kimi-K2-Instruct moonshotai | structural decision-model estimate p=1.00name: Instruct +1 | 1.03T | 128K | $0.57 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| Qwen2.5-VL-7B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 8.29B | 125K | — | Single GPU | Apache 2.0 | 1 | — |
| phi-4 microsoft | structural decision-model estimate p=1.00tag: conversational +1 | 14.7B | 16K | $0.06 | Single high-end GPU | MIT | 3 | — |
| DeepSeek-V3-0324 deepseek-ai | structural decision-model estimate p=0.98tag: conversational +1 | 685B | 160K | $0.24 | Cluster | MIT | 3 | — |
| Llama-4-Scout-17B-16E-Instruct meta-llama | structural decision-model estimate p=0.98name: Instruct +1 | 109B | 1.3M | $0.08 | Multi-GPU node | Llama Community License (… attribution | 4 | — |
| GLM-4.5-Air zai-org | structural tag: conversationalchat template present | 110B | 128K | $0.13 | Multi-GPU node | MIT | 4 | — |
| MiniMax-M2.7 MiniMaxAI | structural decision-model estimate p=0.92tag: conversational +1 | 229B | 200K | $0.21 | Multi-GPU node | other review | 4 | — |
| Qwen2.5-3B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 3.09B | 32K | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 1 | — |
| Qwen2.5-0.5B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 494M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen3-4B Qwen | structural decision-model estimate p=0.70tag: conversational +1 | 4.02B | 40K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Embedding-8B Qwen | structural chat template present | 7.57B | 40K | $0.01 | Single GPU | Apache 2.0 | 2 | — |
| Qwen2.5-Coder-7B-Instruct Qwen | structural decision-model estimate p=0.99name: Instruct +1 | 7.62B | 32K | $0.01 | Single GPU | Apache 2.0 | 2 | — |
| DeepSeek-V4-Pro-0813 deepseek-ai | structural decision-model estimate p=0.95 | 1.65T | 1M | $0.12 | Cluster | MIT | 6 | — |
| Mistral-7B-Instruct-v0.2 mistralai | structural decision-model estimate p=1.00name: Instruct +1 | 7.24B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Unlimited-OCR baidu | structural tag: conversationalchat template present | 3.34B | 32K | — | Single GPU | MIT | 0 | — |
| Qwen3-Coder-Next Qwen | structural tag: conversationalchat template present | 79.7B | 256K | $0.12 | Multi-GPU node | Apache 2.0 | 3 | — |
| Qwen3-VL-4B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 4.44B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen3-30B-A3B Qwen | structural decision-model estimate p=0.83tag: conversational +1 | 30.5B (3B active) | 40K | $0.12 | Single high-end GPU | Apache 2.0 | 2 | — |
| Qwen2.5-VL-3B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 3.75B | 125K | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 1 | — |
| Qwen3-VL-2B-Instruct Qwen | structural decision-model estimate p=0.99name: Instruct +1 | 2.13B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2.5-72B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 72.7B | 32K | $0.36 | Multi-GPU node | Qwen License (qwen) gated-threshold | 3 | — |
| GLM-4.7 zai-org | structural decision-model estimate p=0.94tag: conversational +1 | 358B | 198K | $0.32 | Cluster | MIT | 4 | — |
| Qwen3-1.7B Qwen | structural decision-model estimate p=0.79tag: conversational +1 | 2.03B | 40K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Reranker-0.6B Qwen | structural chat template present | 596M | 40K | $0.01 | Laptop / edge | Apache 2.0 | 2 | — |
| DeepSeek-R1-Distill-Qwen-32B deepseek-ai | structural decision-model estimate p=0.90tag: conversational +1 | 32.8B | 128K | — | Single high-end GPU | MIT | 2 | — |
| DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai | structural decision-model estimate p=0.91tag: conversational +1 | 1.78B | 128K | — | Single GPU | MIT | 1 | — |
| GLM-4.6 zai-org | structural decision-model estimate p=0.94tag: conversational +1 | 357B | 198K | $0.40 | Cluster | MIT | 5 | — |
| DeepSeek-R1-Distill-Qwen-7B deepseek-ai | structural decision-model estimate p=0.90tag: conversational +1 | 7.62B | 128K | $0.15 | Single GPU | MIT | 2 | — |
| multilingual-e5-large-instruct intfloat | structural name: instruct | 560M | 514 | $0.01 | Laptop / edge | MIT | 2 | — |
| Mistral-7B-Instruct-v0.1 mistralai | structural decision-model estimate p=1.00name: Instruct +1 | 7.24B | 32K | — | Single GPU | Apache 2.0 | 2 | — |
| Llama-2-13b-chat-hf meta-llama | structural decision-model estimate p=0.97name: chat +1 | 13.0B | — | — | Single high-end GPU | Llama 2 Community License attribution | 2 | — |
| Qwen2.5-VL-72B-Instruct Qwen | structural decision-model estimate p=0.99name: Instruct +1 | 73.4B | 125K | $0.80 | Multi-GPU node | Qwen License (qwen) gated-threshold | 3 | — |
| Qwen2.5-0.5B Qwen | structural tag: conversationalchat template present | 494M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| gemma-4-E2B-it google | structural decision-model estimate p=0.95name: it +1 | 5.12B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| MiniMax-M2 MiniMaxAI | structural decision-model estimate p=0.94tag: conversational +1 | 229B | 192K | $0.26 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 3 | — |
| Qwen3-VL-235B-A22B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 236B (22B active) | 256K | $0.20 | Multi-GPU node | Apache 2.0 | 3 | — |
| gemma-4-12B-it google | structural decision-model estimate p=0.99name: it +1 | 12.0B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| Llama-2-7b-chat-hf meta-llama | structural decision-model estimate p=0.95name: chat +1 | 6.74B | — | — | Single GPU | Llama 2 Community License attribution | 0 | — |
| Qwen2.5-VL-32B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 33.5B | 125K | — | Multi-GPU node | Apache 2.0 | 2 | — |
| Kimi-K2.7-Code moonshotai | structural decision-model estimate p=0.70tag: conversational +1 | 1.03T | 256K | $0.67 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| DeepSeek-R1-Distill-Qwen-14B deepseek-ai | structural decision-model estimate p=0.93tag: conversational +1 | 14.8B | 128K | $0.20 | Single high-end GPU | MIT | 2 | — |
| Step-3.5-Flash stepfun-ai | structural decision-model estimate p=0.86tag: conversational +1 | 199B | 256K | $0.10 | Multi-GPU node | Apache 2.0 | 3 | — |
| DeepSeek-R1-Distill-Llama-8B deepseek-ai | structural decision-model estimate p=0.91tag: conversational +1 | 8.03B | 128K | $0.05 | Single GPU | MIT | 2 | — |
| gemma-2-9b-it google | structural decision-model estimate p=1.00name: it +1 | 9.24B | 8K | — | Single GPU | Gemma Terms of Use attribution | 2 | — |
| gemma-2-2b-it google | structural decision-model estimate p=1.00name: it +1 | 2.61B | 8K | — | Single GPU | Gemma Terms of Use attribution | 1 | — |
| Qwen3.8-2.4T-A95B Qwen | structural decision-model estimate p=0.98tag: conversational +1 | 2.45T (95B active) | 256K | $2.00 | Cluster | Qwen License (qwen3.8-max) gated-threshold | 5 | — |
| Qwen3-VL-Embedding-2B Qwen | structural chat template present | 2.13B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| UI-TARS-1.5-7B ByteDance-Seed | structural tag: conversationalchat template present | 8.29B | 125K | $0.10 | Single GPU | Apache 2.0 | 3 | — |
| Qwen3-Embedding-4B Qwen | structural chat template present | 4.02B | 40K | $0.02 | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Reranker-4B Qwen | structural chat template present | 4.02B | 40K | $0.03 | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Coder-480B-A35B-Instruct Qwen | structural decision-model estimate p=0.95name: Instruct +1 | 480B (35B active) | 256K | $0.22 | Cluster | Apache 2.0 | 3 | — |
| Llama-3.1-70B-Instruct meta-llama | structural decision-model estimate p=0.95name: Instruct +1 | 70.6B | — | — | Multi-GPU node | Llama 3.1 Community Licen… attribution | 1 | — |
| Qwen2-VL-2B-Instruct Qwen | structural decision-model estimate p=0.98name: Instruct +1 | 2.21B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| DeepSeek-R1-Distill-Llama-70B deepseek-ai | structural decision-model estimate p=0.89tag: conversational +1 | 70.6B | 128K | — | Multi-GPU node | MIT | 2 | — |
| Qwen2.5-14B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 14.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Qwen2-VL-7B-Instruct Qwen | structural decision-model estimate p=0.98name: Instruct +1 | 8.29B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| Kimi-K2-Thinking moonshotai | structural decision-model estimate p=0.95tag: conversational +1 | 1.03T | 256K | $0.60 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 3 | — |
| Qwen2.5-32B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 32.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Llama-3.2-11B-Vision-Instruct meta-llama | structural decision-model estimate p=0.98name: Instruct +1 | 10.7B | — | — | Single high-end GPU | Llama 3.2 Community Licen… attribution | 1 | — |
| DeepSeek-R1-0528-Qwen3-8B deepseek-ai | structural decision-model estimate p=0.99tag: conversational +1 | 8.19B | 128K | — | Single GPU | MIT | 1 | — |
| QwQ-32B Qwen | structural tag: conversationalchat template present | 32.8B | 40K | — | Single high-end GPU | Apache 2.0 | 2 | — |
| DeepSeek-V4-Flash-Vision-Exp deepseek-ai | structural decision-model estimate p=0.94 | 305B | 1M | $0.22 | Cluster | MIT | 2 | — |
| gemma-2-27b-it google | structural decision-model estimate p=1.00name: it +1 | 27.2B | 8K | $0.65 | Single high-end GPU | Gemma Terms of Use attribution | 3 | — |
| Phi-3-mini-4k-instruct microsoft | structural decision-model estimate p=1.00name: instruct +1 | 3.82B | 4K | — | Single GPU | MIT | 1 | — |
| Qwen2.5-Coder-14B-Instruct Qwen | structural decision-model estimate p=0.99name: Instruct +1 | 14.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Qwen2.5-Omni-7B Qwen | structural decision-model estimate p=0.98chat template present | 10.7B | — | — | Single high-end GPU | Apache 2.0 (apache-2.0) | 0 | — |
| Qwen3-VL-32B-Instruct Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 33.4B | 256K | — | Multi-GPU node | Apache 2.0 | 2 | — |
| medgemma-4b-it google | structural decision-model estimate p=0.97name: it +1 | 4.30B | — | — | Single GPU | health-ai-developer-found… review | 0 | — |
| Qwen2.5-Coder-7B Qwen | structural tag: conversationalchat template present | 7.62B | 32K | — | Single GPU | Apache 2.0 | 2 | — |
| Hy3 tencent | structural decision-model estimate p=0.98tag: conversational +1 | 299B | 256K | $0.08 | Cluster | Apache 2.0 | 3 | — |
| GLM-4.5 zai-org | structural decision-model estimate p=0.75tag: conversational +1 | 358B | 128K | $0.60 | Cluster | MIT | 2 | — |
| Qwen3-VL-Embedding-8B Qwen | structural chat template present | 8.14B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen2.5-7B Qwen | structural tag: conversationalchat template present | 7.62B | 128K | $0.10 | Single GPU | Apache 2.0 | 1 | — |
| Kimi-K2-Instruct-0905 moonshotai | structural decision-model estimate p=1.00name: Instruct +1 | 1.03T | 256K | $0.60 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 3 | — |
| MiniMax-M2.1 MiniMaxAI | structural decision-model estimate p=0.94tag: conversational +1 | 229B | 192K | $0.30 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 3 | — |
| Qwen3-VL-235B-A22B-Thinking Qwen | structural decision-model estimate p=0.99tag: conversational +1 | 236B (22B active) | 256K | — | Multi-GPU node | Apache 2.0 | 3 | — |
| GLM-4.5V zai-org | structural decision-model estimate p=0.97tag: conversational +1 | 108B | 64K | $0.60 | Multi-GPU node | MIT | 3 | — |
| diffusiongemma-26B-A4B-it google | structural decision-model estimate p=0.96name: it +1 | 25.8B (4B active) | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| TinyLlama-1.1B-Chat-v1.0 TinyLlama | structural decision-model estimate p=1.00name: Chat +1 | 1.10B | 2K | — | Laptop / edge | Apache 2.0 | 1 | — |
| DeepSeek-Coder-V2-Lite-Instruct deepseek-ai | structural decision-model estimate p=0.95name: Instruct +1 | 15.7B | 160K | — | Single high-end GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen3-Omni-30B-A3B-Instruct Qwen | structural decision-model estimate p=0.98name: Instruct | 35.3B (3B active) | — | — | Multi-GPU node | Apache 2.0 (apache-2.0) | 0 | — |
| Qwen2.5-1.5B Qwen | structural tag: conversationalchat template present | 1.54B | 128K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Phi-3.5-mini-instruct microsoft | structural decision-model estimate p=1.00name: instruct +1 | 3.82B | 128K | — | Single GPU | MIT | 0 | — |
| Meta-Llama-3-70B-Instruct meta-llama | structural decision-model estimate p=0.95name: Instruct +1 | 70.6B | — | — | Multi-GPU node | Llama 3 Community License attribution | 2 | — |
| HunyuanOCR tencent | structural tag: conversationalchat template present | 1.12B | 128K | — | Laptop / edge | tencent-hunyuan-community review | 0 | — |
| LocateAnything-3B nvidia | structural tag: conversationalchat template present | 3.83B | 32K | — | Single GPU | NVIDIA Open Model License… attribution | 0 | — |
| Qwen3-0.6B-Base Qwen | structural tag: conversationalchat template present | 596M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Phi-3.5-vision-instruct microsoft | structural decision-model estimate p=0.99name: instruct +1 | 4.15B | 128K | — | Single GPU | MIT | 0 | — |
| gemma-4-E4B google | structural decision-model estimate p=0.71 | 8.00B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3-4B-Base Qwen | structural tag: conversationalchat template present | 4.02B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2.5-Coder-3B-Instruct Qwen | structural decision-model estimate p=0.98name: Instruct +1 | 3.09B | 32K | $0.01 | Single GPU | Qwen License (qwen-resear… gated-threshold | 2 | — |
| Qwen3-Reranker-8B Qwen | structural chat template present | 8.19B | 40K | $0.05 | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-8B-Base Qwen | structural tag: conversationalchat template present | 8.19B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-VL-8B-Thinking Qwen | structural decision-model estimate p=0.97tag: conversational +1 | 8.77B | 256K | — | Single GPU | Apache 2.0 | 3 | — |
| QwQ-32B-Preview Qwen | structural decision-model estimate p=0.72tag: conversational +1 | 32.8B | 32K | — | Single high-end GPU | Apache 2.0 | 2 | — |
| Qwen2.5-Coder-1.5B-Instruct Qwen | structural decision-model estimate p=0.99name: Instruct +1 | 1.54B | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen2.5-7B-Instruct-1M Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 7.62B | 986K | — | Single GPU | Apache 2.0 | 1 | — |
| medgemma-1.5-4b-it google | structural decision-model estimate p=0.96name: it +1 | 4.30B | — | — | Single GPU | health-ai-developer-found… review | 0 | — |
| Phi-3-mini-128k-instruct microsoft | structural decision-model estimate p=1.00name: instruct +1 | 3.82B | 128K | — | Single GPU | MIT | 0 | — |
| falcon-7b-instruct tiiuae | structural decision-model estimate p=1.00name: instruct +1 | 7.22B | — | — | Single GPU | Apache 2.0 | 0 | — |
| Llama-Guard-3-8B meta-llama | structural tag: conversational | 8.03B | — | — | Single GPU | Llama 3.1 Community Licen… attribution | 2 | — |
| Qwen2.5-3B Qwen | structural tag: conversationalchat template present | 3.09B | 32K | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 1 | — |
| LightOnOCR-2-1B lightonai | structural tag: conversationalchat template present | 1.01B | 16K | — | Laptop / edge | Apache 2.0 | 1 | — |
| GLM-4.6V-Flash zai-org | structural decision-model estimate p=0.98tag: conversational +1 | 10.3B | 128K | $0.30 | Single high-end GPU | MIT | 2 | — |
| Qwen2.5-Coder-1.5B Qwen | structural tag: conversationalchat template present | 1.54B | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| DeepSeek-V3.2-Exp deepseek-ai | structural tag: conversationalchat template present | 685B | 160K | $0.27 | Cluster | MIT | 2 | — |
| Llama-2-70b-chat-hf meta-llama | structural decision-model estimate p=0.94name: chat +1 | 69.0B | — | — | Multi-GPU node | Llama 2 Community License attribution | 1 | — |
| Qwen3-1.7B-Base Qwen | structural tag: conversationalchat template present | 1.72B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Cosmos-Reason2-2B nvidia | structural decision-model estimate p=0.96tag: conversational | 2.44B | — | — | Single GPU | NVIDIA Open Model License… attribution | 0 | — |
| bloomz-560m bigscience | structural decision-model estimate p=0.99 | 559M | 2K | — | Laptop / edge | BLOOM RAIL 1.0 attribution | 0 | — |
| Qwen2.5-Coder-0.5B-Instruct Qwen | structural decision-model estimate p=0.97name: Instruct +1 | 494M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen2.5-Omni-3B Qwen | structural decision-model estimate p=0.98chat template present | 5.54B | — | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 0 | — |
| Qwen2.5-Math-1.5B Qwen | structural tag: conversationalchat template present | 1.54B | 4K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Kimi-Linear-48B-A3B-Instruct moonshotai | structural decision-model estimate p=1.00name: Instruct +1 | 49.1B (3B active) | — | — | Multi-GPU node | MIT | 1 | — |
| gemma-4-E2B google | structural decision-model estimate p=0.81 | 5.12B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| LFM2.5-2.6B LiquidAI | structural decision-model estimate p=0.93tag: conversational +1 | 2.70B | 128K | $0.00 | Single GPU | lfm1.0 review | 1 | — |
| granite-docling-258M ibm-granite | structural tag: conversationalchat template present | 258M | 8K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Qwen3Guard-Gen-0.6B Qwen | structural tag: conversationalchat template present | 752M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| GLM-4.1V-9B-Thinking zai-org | structural decision-model estimate p=0.70tag: conversational +1 | 10.3B | 64K | — | Single high-end GPU | MIT | 0 | — |
| MiMo-V2.6-Pro-RL XiaomiMiMo | structural decision-model estimate p=0.95tag: conversational +1 | 1.02T | 1M | $0.39 | Cluster | MIT | 2 | — |
| DialoGPT-medium microsoft | structural tag: conversationalchat template present | — | 1K | — | — | MIT | 0 | — |
| LFM2.5-1.2B-Instruct LiquidAI | structural decision-model estimate p=1.00name: Instruct +1 | 1.17B | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| chandra-ocr-2 datalab-to | structural tag: conversationalchat template present | 5.30B | 256K | — | Single GPU | OpenRAIL attribution | 0 | — |
| Qwen2.5-14B Qwen | structural tag: conversationalchat template present | 14.8B | 128K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Qianfan-OCR baidu | structural tag: conversationalchat template present | 4.74B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| MiniCPM5-2B openbmb | structural decision-model estimate p=0.96tag: conversational +1 | 2.52B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| deepseek-vl2-tiny deepseek-ai | structural decision-model estimate p=0.85 | 3.37B | — | — | Single GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Llama-4-Maverick-17B-128E-Instruct meta-llama | structural decision-model estimate p=0.95name: Instruct +1 | 402B | 512K | $0.19 | Cluster | Llama Community License (… attribution | 2 | — |
| MiMo-V2.6-Flash-RL XiaomiMiMo | structural decision-model estimate p=0.96tag: conversational +1 | 311B | 1M | $0.09 | Cluster | MIT | 2 | — |
| Hy4-preview tencent | structural decision-model estimate p=0.82tag: conversational +1 | 780B | 1M | $0.75 | Cluster | Apache 2.0 | 3 | — |
| medgemma-27b-text-it google | structural decision-model estimate p=0.99name: it +1 | 27.0B | — | — | Single high-end GPU | health-ai-developer-found… review | 1 | — |
| Laguna-S-2.1 poolside | structural decision-model estimate p=0.73tag: conversational +1 | 118B | 1M | $0.00 | Multi-GPU node | — review | 2 | — |
| Qwen1.5-0.5B Qwen | structural tag: conversationalchat template present | 620M | 32K | — | Laptop / edge | Research / non-commercial… non-commercial | 1 | — |
| Qwen-7B-Chat Qwen | structural decision-model estimate p=1.00name: Chat | 7.72B | 32K | — | Single GPU | tongyi-qianwen-license-ag… review | 0 | — |
| Qwen-VL-Chat Qwen | structural decision-model estimate p=0.98name: Chat | — | 8K | — | — | Not declared review | 0 | — |
| Qwen3-VL-4B-Thinking Qwen | structural decision-model estimate p=0.95tag: conversational +1 | 4.44B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen1.5-0.5B-Chat Qwen | structural decision-model estimate p=1.00name: Chat +1 | 620M | 32K | — | Laptop / edge | Research / non-commercial… non-commercial | 1 | — |
| Qwen2.5-32B Qwen | structural tag: conversationalchat template present | 32.8B | 128K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| gemma-4-31B-it-assistant google | structural name: it | 470M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| surya-ocr-2 datalab-to | structural tag: conversationalchat template present | 686M | 256K | — | Laptop / edge | OpenRAIL attribution | 1 | — |
| Step-3.7-Flash stepfun-ai | structural decision-model estimate p=0.94tag: conversational +1 | 201B | 256K | $0.20 | Multi-GPU node | Apache 2.0 | 3 | — |
| DeepSeek-V2-Lite deepseek-ai | structural decision-model estimate p=0.76tag: conversational +1 | 15.7B | 160K | — | Single high-end GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Inkling-Small thinkingmachines | structural decision-model estimate p=0.99tag: conversational +1 | 266B | 1M | $0.00 | Multi-GPU node | Apache 2.0 | 2 | — |
| translategemma-4b-it google | structural name: ittag: conversational +1 | 4.30B | 128K | — | Single GPU | Gemma Terms of Use attribution | 0 | — |
| Ornith-1.0-9B ornith-ai | structural tag: conversationalchat template present | 1.47M | 256K | — | Laptop / edge | MIT | 1 | — |
| Llama-Guard-4-12B meta-llama | structural tag: conversational | 12.0B | 160K | $0.14 | Single high-end GPU | Llama Community License (… attribution | 2 | — |
| Qwen3-VL-30B-A3B-Thinking Qwen | structural decision-model estimate p=0.96tag: conversational +1 | 31.1B (3B active) | 256K | $0.29 | Single high-end GPU | Apache 2.0 | 2 | — |
| SOLAR-10.7B-Instruct-v1.0 upstage | structural decision-model estimate p=1.00name: Instruct +1 | 10.7B | 4K | — | Single high-end GPU | CC BY-NC 4.0 non-commercial | 1 | — |
| vicuna-7b-v1.5 lmsys | structural decision-model estimate p=1.00 | — | 4K | — | — | Llama 2 Community License attribution | 1 | — |
| GLM-4.6V zai-org | structural decision-model estimate p=0.93tag: conversational +1 | 108B | 128K | $0.30 | Multi-GPU node | MIT | 3 | — |
| gpt-oss-safeguard-20b openai | structural tag: conversationalchat template present | 21.5B | 128K | $0.07 | Single high-end GPU | Apache 2.0 | 2 | — |
| falcon-40b-instruct tiiuae | structural decision-model estimate p=1.00name: instruct | — | — | — | — | Apache 2.0 | 0 | — |
| MiniCPM-o-4_5 openbmb | structural decision-model estimate p=0.98chat template present | 9.37B | 40K | — | Single GPU | Apache 2.0 | 0 | — |
| MiMo-V2.5 XiaomiMiMo | structural decision-model estimate p=0.85tag: conversational +1 | 311B | 1M | $0.12 | Cluster | MIT | 2 | — |
| Llama-3.1-405B-Instruct meta-llama | structural decision-model estimate p=0.99name: Instruct +1 | 406B | — | — | Cluster | Llama 3.1 Community Licen… attribution | 0 | — |
| medgemma-27b-it google | structural decision-model estimate p=0.86name: it +1 | 27.4B | — | — | Single high-end GPU | health-ai-developer-found… review | 0 | — |
| deepseek-coder-6.7b-instruct deepseek-ai | structural decision-model estimate p=0.96name: instruct +1 | 6.74B | 16K | — | Single GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Kimi-VL-A3B-Instruct moonshotai | structural decision-model estimate p=0.99name: Instruct +1 | 16.4B (3B active) | 128K | — | Single high-end GPU | MIT | 0 | — |
| LFM2.5-8B-A1B LiquidAI | structural decision-model estimate p=1.00tag: conversational +1 | 8.47B (1B active) | 125K | — | Single GPU | lfm1.0 review | 0 | — |
| Qwen1.5-1.8B-Chat Qwen | structural decision-model estimate p=1.00name: Chat +1 | 1.84B | 32K | — | Single GPU | Research / non-commercial… non-commercial | 1 | — |
| Qwen3Guard-Gen-8B Qwen | structural tag: conversationalchat template present | 8.19B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2.5-Math-1.5B-Instruct Qwen | structural name: Instructtag: conversational +1 | 1.54B | 4K | — | Laptop / edge | Apache 2.0 | 1 | — |
| MythoMax-L2-13b Gryphe | structural decision-model estimate p=0.99 | — | 4K | $0.08 | — | Other review | 4 | — |
| LFM2.5-24B-A2B LiquidAI | structural tag: conversational | 24.0B (2B active) | — | — | Single high-end GPU | lfm1.0 review | 0 | — |
| MiniCPM5-1B openbmb | structural decision-model estimate p=1.00tag: conversational +1 | 1.08B | 128K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Qwen3-14B-Base Qwen | structural tag: conversationalchat template present | 14.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Phi-3-vision-128k-instruct microsoft | structural decision-model estimate p=0.99name: instruct +1 | 4.15B | 128K | — | Single GPU | MIT | 0 | — |
| Ling-3.0-flash inclusionAI | structural decision-model estimate p=0.98tag: conversational +1 | 127B | 256K | $0.02 | Multi-GPU node | MIT | 3 | — |
| Qwen2.5-Math-7B Qwen | structural tag: conversationalchat template present | 7.62B | 4K | — | Single GPU | Apache 2.0 | 1 | — |
| DeepSeek-V2-Lite-Chat deepseek-ai | structural decision-model estimate p=0.95name: Chat +1 | 15.7B | 160K | — | Single high-end GPU | DeepSeek License (deepsee… attribution | 0 | — |
| MiniCPM-o-2_6 openbmb | structural decision-model estimate p=0.98chat template present | 8.67B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| gemma-4-26B-A4B-it-assistant google | structural name: it | 420M (4B active) | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled Jackrong | structural decision-model estimate p=0.95tag: conversational +1 | 27.8B | 256K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| MiniMax-M3.1-Flash MiniMaxAI | structural tag: conversational | 220B | 977K | $0.15 | Multi-GPU node | MiniMax Model License (mi… gated-threshold | 1 | — |
| QVQ-72B-Preview Qwen | structural tag: conversationalchat template present | 73.4B | 125K | — | Multi-GPU node | Qwen License (qwen) gated-threshold | 1 | — |
| dots.ocr dots-studio | structural tag: conversationalchat template present | 3.04B | 128K | — | Single GPU | MIT | 0 | — |
| Qwen3.5-0.8B-Base Qwen | structural tag: conversationalchat template present | 873M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Qwen2.5-Math-7B-Instruct Qwen | structural name: Instructtag: conversational +1 | 7.62B | 4K | — | Single GPU | Apache 2.0 | 1 | — |
| MiniCPM-V-4.6 openbmb | structural decision-model estimate p=0.91tag: conversational +1 | 1.30B | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Ornith-1.0-35B ornith-ai | structural tag: conversationalchat template present | 665K | 256K | — | Laptop / edge | MIT | 0 | — |
| OvisOCR2 ATH-MaaS | structural tag: conversationalchat template present | 853M | 256K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Molmo-7B-D-0924 allenai | structural decision-model estimate p=0.84tag: conversational +1 | 8.02B | 4K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen2.5-Coder-3B Qwen | structural tag: conversationalchat template present | 3.09B | 32K | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 1 | — |
| Qwen3-Omni-30B-A3B-Thinking Qwen | structural decision-model estimate p=0.98 | 31.7B (3B active) | — | — | Single high-end GPU | Apache 2.0 (apache-2.0) | 0 | — |
| Qwen2.5-14B-Instruct-1M Qwen | structural decision-model estimate p=1.00name: Instruct +1 | 14.8B | 986K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| deepseek-coder-7b-instruct-v1.5 deepseek-ai | structural decision-model estimate p=0.99name: instruct +1 | 6.91B | 4K | — | Single GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen3.5-4B-Base Qwen | structural tag: conversationalchat template present | 4.66B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Llama3-ChatQA-1.5-8B nvidia | structural decision-model estimate p=0.98tag: conversational +1 | 8.03B | 8K | — | Single GPU | Llama 3 Community License attribution | 1 | — |
| d1-3B LiquidAI | structural tag: conversational | 3.12B | — | — | Single GPU | lfm1.0 review | 0 | — |
| Hunyuan-A13B-Instruct tencent | structural decision-model estimate p=1.00name: Instruct +1 | 80.4B (13B active) | 32K | $0.14 | Multi-GPU node | tencent-hunyuan-a13b review | 1 | — |
| Cosmos-Reason2-8B nvidia | structural decision-model estimate p=0.96tag: conversational | 8.77B | — | — | Single GPU | NVIDIA Open Model License… attribution | 0 | — |
| Llama-3.2-1B-Instruct unsloth | structural decision-model estimate p=1.00name: Instruct +1 | 1.24B | 128K | — | Laptop / edge | Llama 3.2 Community Licen… attribution | 0 | — |
| llava-1.5-7b-hf llava-hf | structural decision-model estimate p=1.00tag: conversational +1 | 7.06B | 4K | — | Single GPU | Llama 2 Community License attribution | 0 | — |
| zephyr-7b-alpha HuggingFaceH4 | structural decision-model estimate p=1.00tag: conversational +1 | 7.24B | 32K | — | Single GPU | MIT | 1 | — |
| SmolVLM2-2.2B-Instruct HuggingFaceTB | structural decision-model estimate p=0.73name: Instruct +1 | 2.25B | 8K | — | Single GPU | Apache 2.0 | 0 | — |
| DeepSeek-V3.1-Base deepseek-ai | structural tag: conversationalchat template present | 685B | 160K | — | Cluster | MIT | 0 | — |
| Phi-4-mini-reasoning microsoft | structural tag: conversationalchat template present | 3.84B | 128K | — | Single GPU | MIT | 1 | — |
| DeepSeek-Coder-V2-Instruct deepseek-ai | structural decision-model estimate p=0.92name: Instruct +1 | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen2-VL-72B-Instruct Qwen | structural decision-model estimate p=0.98name: Instruct +1 | 73.4B | 32K | — | Multi-GPU node | tongyi-qianwen review | 0 | — |
| idefics2-8b HuggingFaceM4 | structural decision-model estimate p=0.95 | 8.40B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen1.5-1.8B Qwen | structural tag: conversationalchat template present | 1.84B | 32K | — | Single GPU | Research / non-commercial… non-commercial | 1 | — |
| LFM2.5-350M LiquidAI | structural decision-model estimate p=1.00tag: conversational +1 | 354M | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| Qwen3.5-9B-Base Qwen | structural tag: conversationalchat template present | 9.65B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| NVIDIA-Nemotron-Parse-v1.1 nvidia | structural tag: conversationalchat template present | 957M | 9K | — | Laptop / edge | NVIDIA Open Model License… attribution | 0 | — |
| L3-8B-Stheno-v3.2 Sao10K | structural decision-model estimate p=1.00tag: conversational +1 | 8.03B | 8K | $0.05 | Single GPU | CC BY-NC 4.0 non-commercial | 2 | — |
| Meta-Llama-3.1-8B-Instruct unsloth | structural decision-model estimate p=1.00name: Instruct +1 | 8.03B | 128K | — | Single GPU | Llama 3.1 Community Licen… attribution | 1 | — |
| Qwen1.5-MoE-A2.7B Qwen | structural tag: conversationalchat template present | 14.3B (2.7B active) | 8K | — | Single high-end GPU | tongyi-qianwen review | 0 | — |
| Llama-3_3-Nemotron-Super-49B-v1_5 nvidia | structural decision-model estimate p=1.00tag: conversational +1 | 49.9B | 128K | — | Multi-GPU node | NVIDIA Open Model License… attribution | 0 | — |
| NVLM-D-72B nvidia | structural decision-model estimate p=0.77tag: conversational +1 | 79.4B | — | — | Multi-GPU node | CC BY-NC 4.0 non-commercial | 0 | — |
| Qwen-AgentWorld-35B-A3B Qwen | structural tag: conversationalchat template present | 34.7B (3B active) | 256K | — | Multi-GPU node | Apache 2.0 | 0 | — |
| tiny-Qwen2ForCausalLM-2.5 trl-internal-testing | structural tag: conversationalchat template present | 2.44M | 32K | — | Laptop / edge | Not declared review | 0 | — |
| llava-v1.5-7b liuhaotian | structural decision-model estimate p=0.99 | — | 4K | — | — | Not declared review | 0 | — |
| olmOCR-7B-0225-preview allenai | structural tag: conversationalchat template present | 8.29B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| llava-v1.6-mistral-7b-hf llava-hf | structural decision-model estimate p=0.98tag: conversational +1 | 7.57B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3.5-2B-Base Qwen | structural tag: conversationalchat template present | 2.27B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Huihui-Qwen3.8-27B-abliterated huihui-ai | structural decision-model estimate p=0.87tag: conversational | 27.8B | — | — | Single high-end GPU | Apache 2.0 | 1 | — |
| DeepSeek-V2-Chat deepseek-ai | structural decision-model estimate p=0.96name: Chat +1 | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| DeepSeek-R1-Zero deepseek-ai | structural tag: conversationalchat template present | 684B | 160K | — | Cluster | MIT | 0 | — |
| ReaderLM-v2 jinaai | structural tag: conversationalchat template present | 1.54B | 501K | — | Laptop / edge | CC BY-NC 4.0 non-commercial | 1 | — |
| MiniCPM-V-4_5 openbmb | structural decision-model estimate p=0.94tag: conversational +1 | 8.70B | 40K | — | Single GPU | Apache 2.0 | 0 | — |
| deepseek-coder-1.3b-instruct deepseek-ai | structural decision-model estimate p=0.98name: instruct +1 | 1.35B | 16K | — | Laptop / edge | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen1.5-7B Qwen | structural tag: conversationalchat template present | 7.72B | 32K | — | Single GPU | tongyi-qianwen review | 0 | — |
| Llama-xLAM-2-8b-fc-r Salesforce | structural decision-model estimate p=0.90tag: conversational +1 | 8.03B | 128K | — | Single GPU | CC BY-NC 4.0 non-commercial | 1 | — |
| Idefics3-8B-Llama3 HuggingFaceM4 | structural decision-model estimate p=0.80tag: conversational +1 | 8.46B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| GLM-4-32B-0414 zai-org | structural decision-model estimate p=0.97tag: conversational +1 | 32.6B | 32K | — | Single high-end GPU | MIT | 1 | — |
| InternVL3-78B OpenGVLab | structural decision-model estimate p=0.99tag: conversational +1 | 78.4B | — | — | Multi-GPU node | Qwen License (qwen) gated-threshold | 0 | — |
| functiongemma-270m-it google | structural name: ittag: conversational +1 | 268M | 32K | — | Laptop / edge | Gemma Terms of Use attribution | 0 | — |
| granite-4.2-8b ibm-granite | structural decision-model estimate p=0.93tag: conversational +1 | 8.79B | 128K | $0.06 | Single GPU | Apache 2.0 | 2 | — |
| Qwen1.5-14B-Chat Qwen | structural decision-model estimate p=1.00name: Chat +1 | 14.2B | 32K | — | Single high-end GPU | tongyi-qianwen review | 1 | — |
| aya-expanse-8b CohereLabs | structural decision-model estimate p=0.83tag: conversational | 8.03B | — | — | Single GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| Ornith-1.5-9B ornith-ai | structural decision-model estimate p=0.93tag: conversational +1 | 9.65B | 256K | — | Single GPU | MIT | 1 | — |
| Mage-VL microsoft | structural decision-model estimate p=0.70tag: conversational +1 | 4.74B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| LFM2.5-230M LiquidAI | structural decision-model estimate p=1.00tag: conversational +1 | 230M | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| ERNIE-4.5-21B-A3B-Thinking baidu | structural tag: conversationalchat template present | 21.8B (3B active) | 128K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| Qwen3Guard-Gen-4B Qwen | structural tag: conversationalchat template present | 4.41B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| gemma-1.1-7b-it google | structural decision-model estimate p=1.00name: it +1 | 8.54B | 8K | — | Single GPU | Gemma Terms of Use attribution | 1 | — |
| Kimi-VL-A3B-Thinking moonshotai | structural decision-model estimate p=0.94tag: conversational +1 | 16.4B (3B active) | 128K | — | Single high-end GPU | MIT | 0 | — |
| Hermes-3-Llama-3.1-405B NousResearch | structural decision-model estimate p=1.00tag: conversational +1 | 406B | 128K | $1.00 | Cluster | Llama 3 Community License attribution | 2 | — |
| llama-7b huggyllama | structural tag: conversationalchat template present | 6.74B | 2K | — | Single GPU | Other review | 1 | — |
| North-Mini-Code-1.0 CohereLabs | structural tag: conversationalchat template present | 30.5B | 488K | $0.00 | Single high-end GPU | Apache 2.0 | 1 | — |
| Phi-4-reasoning-plus microsoft | structural decision-model estimate p=0.79tag: conversational +1 | 14.7B | 32K | — | Single high-end GPU | MIT | 1 | — |
| deepseek-llm-7b-chat deepseek-ai | structural decision-model estimate p=0.85name: chat +1 | — | — | — | — | DeepSeek License (deepsee… attribution | 0 | — |
| Bielik-11B-v3.0-Instruct speakleash | structural decision-model estimate p=1.00name: Instruct +1 | 11.2B | — | $0.40 | Single high-end GPU | Apache 2.0 | 1 | — |
| Qwen1.5-4B-Chat Qwen | structural decision-model estimate p=0.99name: Chat +1 | 3.95B | — | — | Single GPU | Research / non-commercial… non-commercial | 1 | — |
| Qwen3-VL-2B-Thinking Qwen | structural decision-model estimate p=0.93tag: conversational +1 | 2.13B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Step3-VL-10B stepfun-ai | structural decision-model estimate p=0.84tag: conversational +1 | 10.2B | 64K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| c4ai-command-r7b-12-2024 CohereLabs | structural decision-model estimate p=0.96tag: conversational | 8.03B | — | — | Single GPU | CC BY-NC 4.0 non-commercial | 1 | — |
| MiniMax-Text-01 MiniMaxAI | structural decision-model estimate p=0.91tag: conversational +1 | 456B | 9.8M | $0.20 | Cluster | Not declared review | 1 | — |
| gemma-1.1-2b-it google | structural decision-model estimate p=1.00name: it +1 | 2.51B | 8K | — | Single GPU | Gemma Terms of Use attribution | 0 | — |
| Llama-3.2-90B-Vision-Instruct meta-llama | structural decision-model estimate p=0.99name: Instruct +1 | 88.6B | — | — | Multi-GPU node | Llama 3.2 Community Licen… attribution | 1 | — |
| Ornith-1.5-35B-A3B ornith-ai | structural decision-model estimate p=0.84tag: conversational +1 | 36.0B (3B active) | 256K | — | Multi-GPU node | MIT | 0 | — |
| translategemma-12b-it google | structural name: ittag: conversational +1 | 12.2B | 128K | — | Single high-end GPU | Gemma Terms of Use attribution | 0 | — |
| MiniMax-M1-80k MiniMaxAI | structural decision-model estimate p=0.85tag: conversational +1 | 456B | 9.8M | $0.55 | Cluster | Apache 2.0 | 1 | — |
| StableBeluga2 stabilityai | structural decision-model estimate p=0.97 | — | — | — | — | Not declared review | 0 | — |
| MiniMax-VL-01 MiniMaxAI | structural decision-model estimate p=0.95tag: conversational +1 | 456B | 8K | — | Cluster | Not declared review | 0 | — |
| Solar-Open-100B upstage | structural decision-model estimate p=0.84tag: conversational +1 | 103B | 128K | — | Multi-GPU node | upstage-solar-license review | 0 | — |
| codegemma-7b-it google | structural decision-model estimate p=0.99name: it +1 | 8.54B | 8K | — | Single GPU | Gemma Terms of Use attribution | 1 | — |
| olmOCR-2-7B-1025 allenai | structural tag: conversationalchat template present | 8.29B | 125K | — | Single GPU | Apache 2.0 | 1 | — |
| Hermes-3-Llama-3.1-70B NousResearch | structural decision-model estimate p=1.00tag: conversational +1 | 70.6B | 128K | $0.70 | Multi-GPU node | Llama 3 Community License attribution | 3 | — |
| MiniCPM-Llama3-V-2_5 openbmb | structural decision-model estimate p=0.99tag: conversational +1 | 8.54B | 8K | — | Single GPU | Not declared review | 1 | — |
| Llama-Guard-3-1B meta-llama | structural tag: conversational | 1.50B | — | — | Laptop / edge | Llama 3.2 Community Licen… attribution | 0 | — |
| Fara-7B microsoft | structural tag: conversationalchat template present | 8.29B | 125K | — | Single GPU | MIT | 0 | — |
| Meta-Llama-Guard-2-8B meta-llama | structural tag: conversational | 8.03B | — | — | Single GPU | Llama 3 Community License attribution | 1 | — |
| EXAONE-4.5-33B LGAI-EXAONE | structural decision-model estimate p=0.82tag: conversational +1 | 34.4B | 256K | — | Multi-GPU node | exaone review | 0 | — |
| deepseek-moe-16b-chat deepseek-ai | structural decision-model estimate p=0.99name: chat +1 | 16.4B | — | — | Single high-end GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen1.5-7B-Chat Qwen | structural decision-model estimate p=0.95name: Chat +1 | 7.72B | — | — | Single GPU | tongyi-qianwen review | 0 | — |
| DeepSeek-V2 deepseek-ai | structural decision-model estimate p=0.76tag: conversational +1 | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| openchat-3.5-1210 openchat | structural decision-model estimate p=1.00tag: conversational | 7.24B | — | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen-14B-Chat Qwen | structural decision-model estimate p=0.98name: Chat | 14.2B | — | — | Single high-end GPU | Not declared review | 0 | — |
| InternVL3-8B OpenGVLab | structural decision-model estimate p=0.99tag: conversational +1 | 7.94B | — | — | Single GPU | Apache 2.0 (qwen) | 0 | — |
| MiMo-7B-RL XiaomiMiMo | structural decision-model estimate p=0.84tag: conversational +1 | 7.83B | 32K | — | Single GPU | MIT | 0 | — |
| granite-3.3-8b-instruct ibm-granite | structural decision-model estimate p=1.00name: instruct +1 | 8.17B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| CodeQwen1.5-7B-Chat Qwen | structural decision-model estimate p=0.91name: Chat +1 | 7.25B | — | — | Single GPU | tongyi-qianwen review | 0 | — |
| InternVL3-1B OpenGVLab | structural decision-model estimate p=0.98tag: conversational +1 | 938M | — | — | Laptop / edge | Apache 2.0 (qwen) | 0 | — |
| DialoGPT-large microsoft | structural tag: conversationalchat template present | — | 1K | — | — | MIT | 0 | — |
| Kimi-VL-A3B-Thinking-2506 moonshotai | structural decision-model estimate p=0.86tag: conversational +1 | 16.4B (3B active) | 128K | — | Single high-end GPU | MIT | 0 | — |
| PaddleOCR-VL-1.6 PaddlePaddle | structural tag: conversationalchat template present | 959M | 128K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Tongyi-DeepResearch-30B-A3B Alibaba-NLP | structural tag: conversational | 30.5B (3B active) | — | — | Single high-end GPU | Apache 2.0 | 0 | — |
| deepseek-coder-33b-instruct deepseek-ai | structural decision-model estimate p=0.87name: instruct +1 | 33.3B | — | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen3-30B-A3B-Base Qwen | structural tag: conversational | 30.5B (3B active) | — | — | Single high-end GPU | Apache 2.0 | 0 | — |
| c4ai-command-r-v01 CohereLabs | structural decision-model estimate p=0.94tag: conversational | 35.0B | — | — | Multi-GPU node | CC BY-NC 4.0 non-commercial | 0 | — |
| Qwen2.5-Coder-32B Qwen | structural tag: conversational | 32.8B | — | — | Single high-end GPU | Apache 2.0 | 1 | — |
| granite-vision-4.1-4b ibm-granite | structural tag: conversational | 4.00B | — | — | Single GPU | Apache 2.0 | 0 | — |
| Cosmos-Reason1-7B nvidia | structural tag: conversationalchat template present | 8.29B | 125K | — | Single GPU | NVIDIA Open Model License… attribution | 0 | — |
| Qwen2.5-Coder-14B Qwen | structural tag: conversational | 14.8B | — | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Phi-3-medium-4k-instruct microsoft | structural decision-model estimate p=1.00name: instruct +1 | 14.0B | — | — | Single high-end GPU | MIT | 1 | — |
| Laguna-XS-2.1 poolside | structural tag: conversational | 33.4B | — | — | Multi-GPU node | — review | 1 | — |
| EXAONE-3.0-7.8B-Instruct LGAI-EXAONE | structural decision-model estimate p=0.99name: Instruct +1 | 7.82B | — | — | Single GPU | exaone review | 0 | — |
| Phi-4-reasoning microsoft | structural tag: conversational | 14.7B | — | — | Single high-end GPU | MIT | 0 | — |
| gemma-4-E4B-it-assistant google | structural decision-model estimate p=0.99name: it | 78.8M | — | — | Laptop / edge | Apache 2.0 | 0 | — |
| deepseek-vl-7b-chat deepseek-ai | structural decision-model estimate p=0.88name: chat | 7.34B | — | — | Single GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen3.5-35B-A3B-Base Qwen | structural tag: conversational | 36.0B (3B active) | — | — | Multi-GPU node | Apache 2.0 | 0 | — |
| DeepSeek-V2.5-1210 deepseek-ai | structural tag: conversational | 236B | — | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| Nemotron-Research-Reasoning-Qwen-1.5B nvidia | structural decision-model estimate p=0.77tag: conversational | 1.78B | — | — | Single GPU | CC BY-NC 4.0 non-commercial | 1 | — |
| Intern-Decision-4B internlm | structural tag: conversationalchat template present | 4.54B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Intern-Decision-0.8B internlm | structural tag: conversationalchat template present | 853M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Winnow-12B EldanRing | structural decision-model estimate p=0.79tag: conversational +1 | — | 256K | — | — | Apache 2.0 | 0 | — |
| JevK5 alibiserikbay | structural tag: conversationalchat template present | 4.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Intern-Decision-2B internlm | structural tag: conversationalchat template present | 2.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Tev1-4B-experimental togethercomputer | structural tag: conversationalchat template present | 4.66B | 256K | $0.04 | Single GPU | Not declared review | 1 | — |
| Tev1-0.8B-experimental togethercomputer | structural tag: conversationalchat template present | 873M | 256K | — | Laptop / edge | Not declared review | 0 | — |
| xor juspay | structural tag: conversationalchat template present | 35.1B | 256K | — | Multi-GPU node | Apache 2.0 | 0 | — |
| LFM2.5-350M-RLCD notnotsamuel | structural tag: conversationalchat template present | 354M | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| openjev openjev | structural chat template present | 27.4B | 256K | — | Single high-end GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| Jev-Omni akhilaaa3 | structural chat template present | 12.0B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| JEV-27B autotrust | structural chat template present | 26.9B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| Bespoke-Nimble-9B bespokelabs | structural chat template present | — | — | — | — | Apache 2.0 | 0 | — |
| kev-9b jaredpalmer | structural chat template present | — | — | — | — | Apache 2.0 | 0 | — |
| lev interfaze-ai | structural chat template present | — | — | — | — | Apache 2.0 | 0 | — |
| decider-2b Mapika | structural chat template present | 1.88B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| decider-4b Mapika | structural chat template present | 4.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| LFM2.5-2.6B-RLCD monotykamary | structural tag: conversationalchat template present | 2.70B | 128K | — | Single GPU | lfm1.0 review | 0 | — |
| system-one-qwen3.5-4b-scorer-v2b pngwn | structural chat template present | — | — | — | — | CC BY-NC 4.0 non-commercial | 0 | — |
| this-that-model-1.0 flock-io | structural chat template present | 1.88B | 256K | — | Single GPU | MIT | 0 | — |
| decider-35b-a3b-nvfp4 Mapika | structural chat template present | 17.9B (3B active) | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| Bespoke-Nimble-9B-v2 bespokelabs | structural chat template present | — | — | — | — | Apache 2.0 | 0 | — |
| this-that-model-1.2 flock-io | structural chat template present | 1.88B | 256K | — | Single GPU | MIT | 0 | — |
| Eikos-27B-FP8 caiovicentino1 | structural chat template present | 27.8B | 256K | — | Single high-end GPU | MIT | 0 | — |
| blink-27b thegovind | structural chat template present | 26.9B | 256K | — | Single high-end GPU | Research / non-commercial… non-commercial | 0 | — |
| jpt-0.8b kirp | structural tag: conversationalchat template present | 853M | 256K | — | Laptop / edge | CC BY-NC 4.0 non-commercial | 0 | — |
| jebadiah-27b frontier-infra | structural tag: conversationalchat template present | 27.8B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
No model matches every constraint. Loosen one, or switch the evidence filter back to any.
How to read this
- measured a third-party leaderboard row for this model. Settings (agent harness, edit format, prompt) differ between boards; compare within a benchmark, not across.
- author-reported a number the model author published in the card or eval files. Not reproduced by us.
- structural a deterministic signal from the name, config or chat template, or a decision-model estimate. A weak signal: it says the model was built or tagged for the job, not how well it does it. "decision-model estimate" chips are a probability from the Jev decision model, not a measurement.
- Runs on is the memory class of the BF16 weights (method); choosing a class shows that class and smaller. Quantized builds may fit a class lower.
- Price from is the cheapest observed hosted input price, USD per million tokens; models with no observed price are hidden when a ceiling is set. License friction: permissive = none or attribution-only; high = non-commercial.
- Ordering within a tier is the watch-list score (Hub likes, downloads, recency), not a quality verdict.
Subscribe
Follow "Chat and follow instructions"
- /feeds/for/chat-instruct.xml(RSS 2.0) · one item per model with measured or author-reported evidence for this job
- /feeds/for/chat-instruct.json(JSON Feed 1.1) · same items, JSON Feed
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.