Up to date
Qwen Apache 2.0 out 2 years ago
1.54B parameters, text in, text out, 32K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #47 in LLMs · score 108.5 method v1 Sources 3 Downloads 30d 4.7M · #33 of 619 tracked
Changed this week: 26 new quantized builds on the Hub (350 in all).2026-10-24 · 22 new quantized builds on the Hub (346 in all).2026-10-24
Picked by rule from 32 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 2 picks above, plus these 23. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | Featherless | — | — | — | — | Oct 25 |
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; heavily run locally (350 quantized builds); a big base for builders (3,764 fine-tunes, adapters and merges).
Top Spaces running it: pliny-the-prompter/obliteratus ♥ 621 · cvachet/pdf-chatbot ♥ 382 · embedl/hfviewer ♥ 181 · build-small-hackathon/llm-cinema ♥ 110
Weights only, an estimate: leave room for the KV cache. Method
About 0.9 GB at INT4, 1.9 GB at FP8, 3.7 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2024-09-17), amber triangles are 5 dated articles (each links to it), grey ticks are repo commits.
4,114 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | Qwen2ForCausalLM |
| Model type | qwen2 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 1,543,714,304 |
| Size band | S |
| MoE | no |
| Context length | 32,768 (config.json max_position_embeddings) |
| Languages | en |
| Papers | arXiv:2407.10671 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · Qwen2ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen2ForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for Qwen2.5-1.5B-Instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 3.7 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 1.9 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.9 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Base model: Qwen/Qwen2.5-1.5B
quantized: 350finetune: 2,025adapter: 1,649merge: 90
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| MaziyarPanahi/Qwen2.5-1.5B-Instruct-GGUF | quantized | GGUF | — | — | — | MaziyarPanahi | 12 | 11.6M |
| Qwen/Qwen2.5-1.5B-Instruct-AWQ | quantized | AWQ | 1.78B | S | apache-2.0 | Qwen | 12 | 6.7M |
| Qwen/Qwen2.5-1.5B-Instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | Qwen | 186 | 3.2M |
| litert-community/Qwen2.5-1.5B-Instruct | finetune | — | — | — | apache-2.0 | litert-community | 57 | 889.8k |
| unsloth/Qwen2.5-1.5B-Instruct-unsloth-bnb-4bit | quantized | -bnb | 1.58B | S | apache-2.0 | unsloth | 5 | 887.9k |
| unsloth/Qwen2.5-1.5B-Instruct | finetune | — | 1.54B | S | apache-2.0 | unsloth | 10 | 611.4k |
| unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit | quantized | -bnb | 1.58B | S | apache-2.0 | unsloth | 6 | 408.4k |
| SakanaAI/TinySwallow-1.5B | finetune | — | 1.54B | S | apache-2.0 | SakanaAI | 35 | 379.8k |
| bartowski/Qwen2.5-1.5B-Instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | bartowski | 23 | 355.4k |
| mlc-ai/Qwen2.5-1.5B-Instruct-q4f16_1-MLC | quantized | — | — | — | — | mlc-ai | 2 | 293.1k |
| Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4 | quantized | GPTQ | 1.54B | S | apache-2.0 | Qwen | 9 | 273.6k |
| BytedanceDouyinContent/SAIL-VL-1d6-8B | finetune | — | 8.33B | M | apache-2.0 | BytedanceDouyinContent | 15 | 190.9k |
| SriSanthM/Qwen-1.5B-Tweet-Generations | adapter | — | — | — | — | SriSanthM | 2 | 155.1k |
| SakanaAI/TinySwallow-1.5B-Instruct | finetune | — | 1.54B | S | apache-2.0 | SakanaAI | 61 | 109.5k |
| Efficient-Large-Model/Fast_dLLM_v2_1.5B | finetune | — | 1.54B | S | apache-2.0 | Efficient-Large-Model | 14 | 110.5k |
| ystemsrx/Qwen2.5-Sex | adapter | GGUF | 1.54B | S | apache-2.0 | ystemsrx | 208 | 97.7k |
| eth-nlped/Qwen2.5-1.5B-pedagogical-rewardmodel | finetune | — | 1.54B | S | cc-by-4.0 | eth-nlped | 4 | 104.2k |
| JackKozmo29/depguard-jev-style-1.5b | finetune | — | 1.54B | S | apache-2.0 | JackKozmo29 | 1 | 68.5k |
| JackKozmo29/mailguard-jev-style-1.5b | finetune | — | 1.54B | S | apache-2.0 | JackKozmo29 | 1 | 68.4k |
| JackKozmo29/sevclassifier-jev-style-1.5b | finetune | — | 1.54B | S | apache-2.0 | JackKozmo29 | 1 | 67.1k |
| JackKozmo29/codeguard-jev-style-1.5b | finetune | — | 1.54B | S | apache-2.0 | JackKozmo29 | 1 | 67k |
| QuantFactory/Qwen2.5-Sex-GGUF | adapter | GGUF | — | — | apache-2.0 | QuantFactory | 35 | 64.5k |
| nvidia/Eagle2-2B | merge | — | 2.21B | M | cc-by-nc-4.0 | nvidia | 37 | 64.3k |
| prismor/prompt-guard-1.5b | adapter | — | 1.54B | S | apache-2.0 | prismor | 0 | 65.9k |
| katanemo/Arch-Router-1.5B | finetune | — | 1.54B | S | other | katanemo | 279 | 46.3k |
| csuhan/Tar-1.5B | finetune | — | 2.57B | M | apache-2.0 | csuhan | 2 | 53.8k |
| Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct | finetune | — | 1.54B | S | apache-2.0 | Vikhrmodels | 15 | 52.3k |
| lmstudio-community/Qwen2.5-1.5B-Instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | lmstudio-community | 2 | 50.4k |
| Sedibaai/SedibaLM | finetune | — | 1.54B | S | cc-by-sa-4.0 | Sedibaai | 0 | 47.1k |
| open-thoughts/OpenThinker3-1.5B | finetune | — | 1.54B | S | apache-2.0 | open-thoughts | 16 | 44.2k |
| BytedanceDouyinContent/SAIL-VL-1d5-2B | finetune | — | 2.47B | M | apache-2.0 | BytedanceDouyinContent | 12 | 39.8k |
| SakanaAI/TinySwallow-1.5B-Instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | SakanaAI | 30 | 27.6k |
| shibing624/chinese-text-correction-1.5b | finetune | — | 1.54B | S | apache-2.0 | shibing624 | 13 | 24.9k |
| onnx-community/Qwen2.5-1.5B-Instruct | quantized | — | — | — | — | onnx-community | 6 | 23.7k |
| mradermacher/Qwen2.5-1.5B-Instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 23k |
| OpenVINO/Qwen2.5-1.5B-Instruct-int4-ov | quantized | int4 | — | — | apache-2.0 | OpenVINO | 2 | 22.4k |
| Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8 | quantized | GPTQ | 1.54B | S | apache-2.0 | Qwen | 11 | 21.3k |
| BAAI/Aquila-VL-2B-llava-qwen | finetune | — | 2.18B | M | apache-2.0 | BAAI | 62 | 18.1k |
| legraphista/Qwen2.5-1.5B-Instruct-IMat-GGUF | quantized | GGUF | — | — | apache-2.0 | legraphista | 0 | 19.6k |
| mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 18.7k |
| Date | Commit | SHA |
|---|---|---|
| 2024-09-25 | Update metadata: Add library_name to Transformers (#1) | 989aa79 |
| 2024-09-19 | Upload ./tokenizer_config.json with huggingface_hub | 5fee7c4 |
| 2024-09-18 | update README & LICENSE | 2fd5061 |
| 2024-09-18 | Update tokenizer_config.json | b9d14db |
| 2024-09-17 | Update README.md | 582efe6 |
| 2024-09-17 | Upload folder using huggingface_hub | 775b11a |
| 2024-09-17 | Create README.md | f89e156 |
| 2024-09-17 | initial commit | e52ab42 |
Hosted endpoints observed for Qwen2.5-1.5B-Instruct, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Featherless hf | Qwen/Qwen2.5-1.5B-Instruct | — | — | — | — | — | — | — | live | 2026-10-25 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:32 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:00 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
