All models
Every open model on the watch list in one table, in watch-list rank order. Pick a preset for your job; the choice rides in the URL, so a link shares your view.
- Fastest first token112msDeepSeek-V4.1-FlashTogether AI via huggingface.co, 2026-10-25
- Cheapest with tool calls$0.010per 1M inQwen3-Embedding-8BDeepInfra via huggingface.co, 2026-10-25
- Most fine-tuned 2025 base2.6kfine-tunesQwen3-4B-Instruct-2507Hugging Face base-model tags, 2026-10-25
Ranked by the watch-list score: Hub likes, downloads, trending and recency. A starting order, not a verdict.
The floor
Every view leaves out test fixtures, models whose size didn't parse, and closed models (unless you ask for them). $0 endpoints show as a free tier and never count as cheapest; classifiers and guards never enter a speed sort. How the rank works.
Kind: All kinds · LLMs · Embeddings · Decision models · Closed
577 models match, first 60 shown. Data observed 2026-10-25 06:54 UTC, Hub snapshot 2026-10-25. Hover a figure for its source and date.
| # | Evidence | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | NanoJevC-Tianyu | — | — | 0 | — | 0 | — | |||
| 2 | SolomonDoccyHealth | — | — | 0 | — | 0 | — | |||
| 3 | Lumma-fev-0.1bFrontiersMind | 154M | — | 0 | ~0.1 GB | 0 | — | |||
| 4 | Lumma-fev-0.6bFrontiersMind | 649M | — | 0 | ~0.4 GB | 0 | — | |||
| 5 | sokudan-ja-310mGeneLab | 315M | — | 0 | ~0.2 GB | 0 | — | |||
| 6 | bosun-v3.1-0.6bHanno-Labs | — | — | 0 | — | +2 | — | |||
| 7 | bosun-v3.1-1.7bHanno-Labs | — | — | 0 | — | +1 | — | |||
| 8 | hopper-gHopitAI | — | — | 0 | — | 0 | — | |||
| 9 | decider-2bMapika | 1.88B | — | 0 | ~1.1 GB | +3 | — | |||
| 10 | decider-35b-a3b-nvfp4Mapika | 17.9B 3B active | — | 0 | ~11 GB | 0 | — | |||
| 11 | decider-4bMapika | 4.21B | — | 0 | ~2.5 GB | +1 | — | |||
| 12 | mojevMoLeMo-Lab | 854M | — | 0 | ~0.5 GB | 0 | — | |||
| 13 | Julia-1SupersonicLabs | 144M | — | 0 | ~0.1 GB | +7 | — | |||
| 14 | NeoHorse-Jev-4BTokenRhythm | — | — | 0 | — | +1 | — | |||
| 15 | Jev-Omniakhilaaa3 | 12.0B | — | 0 | ~7.2 GB | +14 | — | |||
| 16 | JEV-27Bautotrust | 26.9B | — | 0 | ~16 GB | -5 | — | |||
| 17 | Bespoke-Nimble-9Bbespokelabs | — | — | 0 | — | +3 | — | |||
| 18 | Bespoke-Nimble-9B-v2bespokelabs | — | — | 0 | — | 0 | — | |||
| 19 | Bespoke-Nimble-9B-v3bespokelabs | — | — | 0 | — | +2 | — | |||
| 20 | Eikos-27B-FP8caiovicentino1 | 27.8B | — | 0 | ~17 GB | 0 | — | |||
| 21 | layaconvaiinnovations | 421M | — | 0 | ~0.3 GB | +135 | — | |||
| 22 | laya-multilingualconvaiinnovations | 322M | — | 0 | ~0.2 GB | +12 | — | |||
| 23 | laya-typed-decisionsconvaiinnovations | 421M | — | 0 | ~0.3 GB | +2 | — | |||
| 24 | GLiNER2.5-Decidefastino | 486M | — | 0 | ~0.3 GB | +11 | — | |||
| 25 | gliner2.5-base-v1fastino | 194M | — | 0 | ~0.1 GB | 0 | — | |||
| 26 | gliner2.5-multi-v1fastino | 287M | — | 0 | ~0.2 GB | +7 | — | |||
| 27 | this-that-model-1.0flock-io | 1.88B | — | 0 | ~1.1 GB | 0 | — | |||
| 28 | this-that-model-1.2flock-io | 1.88B | — | 0 | ~1.1 GB | +1 | — | |||
| 29 | jebadiah-27bfrontier-infra | 27.8B | — | 0 | ~17 GB | 0 | — | |||
| 30 | rlcd-modernbert-151mheman10x | 151M | — | 0 | ~0.1 GB | +1 | — | |||
| 31 | levinterfaze-ai | — | — | 0 | — | +3 | — | |||
| 32 | kev-0.8bjaredpalmer | — | — | 0 | — | +3 | — | |||
| 33 | kev-4bjaredpalmer | — | — | 0 | — | +24 | — | |||
| 34 | kev-9bjaredpalmer | — | — | 0 | — | +3 | — | |||
| 35 | jpt-0.8bkirp | 853M | — | 0 | ~0.5 GB | 0 | — | |||
| 36 | jpt-4bkirp | 4.54B | — | 0 | ~2.7 GB | +1 | — | |||
| 37 | jpt-9bkirp | 9.41B | — | 0 | ~5.6 GB | 0 | — | |||
| 38 | lavoirmoganai | 422M | — | 0 | ~0.3 GB | 0 | — | |||
| 39 | LFM2.5-2.6B-RLCDmonotykamary | 2.70B | — | 0 | ~1.6 GB | 0 | — | |||
| 40 | openjevopenjev | 27.4B | — | 0 | ~16 GB | +21 | — | |||
| 41 | pplx-decider-v1-27bperplexity-ai | 26.1B | — | 0 | ~16 GB | +7 | — | |||
| 42 | system-one-qwen3.5-4b-scorer-v2bpngwn | — | — | 0 | — | 0 | — | |||
| 43 | rune-26b-a4b-GGUFsurogate | 25.8B | — | 0 | ~16 GB | 0 | — | |||
| 44 | blink-27bthegovind | 26.9B | — | 0 | ~16 GB | 0 | — | |||
| 45 | metask-jev-4b-policy-mixwayfind | 4.54B | — | 0 | ~2.7 GB | 0 | — | |||
| 46 | Qwen3.8-27BQwen | 27.8B | $0.020 | 23 | ~17 GB | +434 | 5/5 | |||
| 47 | bge-m3BAAI | — | $0.010 | 3 | — | +23 | — | |||
| 48 | gpt-oss-120bopenai | 117B | $0.030 | 27 | ~70 GB | +22 | 5/5 | |||
| 49 | all-mpnet-base-v2sentence-transformers | 109M | $0.005 | 2 | ~0.1 GB | +5 | — | |||
| 50 | GLM-5.3-Flashzai-org | 321B | $0.018 | 35 | ~193 GB | +59 | 5/5 | |||
| 51 | gpt-oss-20bopenai | 20.9B | $0.018 | 13 | ~13 GB | +23 | 5/5 | |||
| 52 | paraphrase-multilingual-MiniLM-L12-v2sentence-transformers | 118M | — | 1 | ~0.1 GB | +12 | — | |||
| 53 | gemma-4-26B-A4B-itgoogle | 25.8B 4B active | $0.042 | 16 | ~16 GB | +30 | 4/5 | |||
| 54 | multilingual-e5-largeintfloat | 560M | $0.010 | 2 | ~0.3 GB | +6 | — | |||
| 55 | embeddinggemma-300mgoogle | 303M | $0.002 | 2 | ~0.2 GB | +25 | — | |||
| 56 | GLM-5.3zai-org | 753B | $0.075 | 38 | ~452 GB | +60 | — | |||
| 57 | Qwen3-Embedding-0.6BQwen | 596M | $0.010 | 1 | ~0.4 GB | +14 | — | |||
| 58 | Kimi-K3moonshotai | 2.78T | $0.23 | 22 | ~1668 GB | +68 | 5/5 | |||
| 59 | gemma-4-31B-itgoogle | 31.3B | $0.10 | 14 | ~19 GB | +46 | — | |||
| 60 | bge-base-en-v1.5BAAI | 109M | $0.005 | 2 | ~0.1 GB | +6 | — |
Evidence marks, left to right: coding, tools, reasoning, long docs, vision, chat. measured on a third-party board, author-reported, structural, none yet. Each mark links to its job from the model page. INT4 is an estimate of the weights alone (method).