Up to date
Qwen Apache 2.0 out 2 years ago
7.62B parameters, text in, text out, 4K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #417 in LLMs · score 79 method v1 Sources 3 Downloads 30d 35.7k · #410 of 619 tracked
Picked by rule from 25 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; 15 quantized builds for local use; a big base for builders (1,108 fine-tunes, adapters and merges).
Top Spaces running it: Rickiiiii/Qwen-Qwen2.5-Math-7B ♥ 2
Weights only, an estimate: leave room for the KV cache. Method
About 4.6 GB at INT4, 9.1 GB at FP8, 18 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 (2024-09-16), amber triangles are 5 dated articles (each links to it), grey ticks are repo commits.
1,123 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.
The model is designed to solve English and Chinese math problems using Chain-of-Thought and Tool-integrated Reasoning.[1]
Generated 2026-10-07 15:09 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
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: 7,615,616,512 |
| Size band | M |
| MoE | no |
| Context length | 4,096 (config.json max_position_embeddings) |
| Languages | en |
| Papers | arXiv:2409.12122 |
| 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-Math-7B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 18 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 9.1 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.6 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Base model: Qwen/Qwen2.5-7B
finetune: 1,031quantized: 15merge: 57adapter: 20
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| ByteDance-Seed/BFS-Prover-V1-7B | finetune | — | 7.62B | M | apache-2.0 | ByteDance-Seed | 26 | 933.7k |
| open-r1/Qwen2.5-Math-7B-RoPE-300k | finetune | — | 7.62B | M | apache-2.0 | open-r1 | 5 | 29.7k |
| unsloth/Qwen2.5-Math-7B | finetune | — | 7.62B | M | apache-2.0 | unsloth | 3 | 23.2k |
| sail/Qwen2.5-Math-7B-Oat-Zero | finetune | — | 7.62B | M | apache-2.0 | sail | 6 | 20.6k |
| unsloth/Qwen2.5-Math-7B-bnb-4bit | quantized | -bnb | 7.82B | M | apache-2.0 | unsloth | 3 | 20.7k |
| nvidia/OpenMath-Nemotron-7B | finetune | — | 7.62B | M | cc-by-4.0 | nvidia | 19 | 19.8k |
| FrenzyMath/REAL-Prover | finetune | — | 7.62B | M | apache-2.0 | FrenzyMath | 0 | 20.7k |
| BayesRL/Qwen2.5Math-IVON-SFT-7B | finetune | — | 7.62B | M | apache-2.0 | BayesRL | 0 | 19.4k |
| PhysicsWallahAI/Aryabhata-1.0 | finetune | — | 7.62B | M | cc-by-nc-4.0 | PhysicsWallahAI | 110 | 12.9k |
| DevQuasar-8/Qwen.Qwen2.5-Math-7B-GGUF | quantized | GGUF | — | — | — | DevQuasar-8 | 0 | 15.9k |
| QuantFactory/Qwen2.5-Math-7B-Instruct-GGUF | quantized | GGUF | — | — | apache-2.0 | QuantFactory | 2 | 13.1k |
| BayesRL/Llama3.1-IVON-SFT-8B | finetune | — | 8.03B | M | apache-2.0 | BayesRL | 0 | 11k |
| Mungert/OpenMath-Nemotron-7B-GGUF | quantized | GGUF | — | — | cc-by-4.0 | Mungert | 3 | 9k |
| Mungert/Aryabhata-1.0-GGUF | quantized | GGUF | — | — | apache-2.0 | Mungert | 0 | 8.9k |
| mradermacher/Qwen2.5-Math-7B-i1-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 0 | 8.7k |
| ByteDance-Seed/BFS-Prover-V2-7B | finetune | — | 7.62B | M | apache-2.0 | ByteDance-Seed | 7 | 7.2k |
| QuantFactory/BFS-Prover-GGUF | quantized | GGUF | — | — | apache-2.0 | QuantFactory | 1 | 6.4k |
| hkust-nlp/Qwen-2.5-Math-7B-SimpleRL-Zero | finetune | — | 7.62B | M | apache-2.0 | hkust-nlp | 3 | 5.9k |
| WiroAI/WiroAI-Finance-Qwen-7B | finetune | — | 7.62B | M | apache-2.0 | WiroAI | 10 | 4.3k |
| mradermacher/Qwen2.5-Math-7B-GGUF | quantized | GGUF | — | — | apache-2.0 | mradermacher | 1 | 3.8k |
| jinachris/PURE-PRM-7B | finetune | — | 7.07B | M | apache-2.0 | jinachris | 4 | 3.3k |
| luckeciano/Qwen-2.5-7B-GRPO-NoKL-1e-05-24 | finetune | — | 7.62B | M | — | luckeciano | 0 | 2.9k |
| Yuuta208/Qwen2.5-7B-Instruct-Qwen2.5-Math-7B-Merged-task_arithmetic-26 | merge | — | 7.62B | M | — | Yuuta208 | 0 | 2.7k |
| Yuuta208/Qwen2.5-7B-Instruct-Qwen2.5-Math-7B-Merged-della-27 | merge | — | 7.62B | M | — | Yuuta208 | 0 | 2.4k |
| nvidia/NFT-7B | finetune | — | 7.62B | M | other | nvidia | 3 | 2.1k |
| luckeciano/Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv | finetune | — | 7.62B | M | — | luckeciano | 0 | 2.2k |
| featherless-ai-quants/Qwen-Qwen2.5-Math-7B-GGUF | quantized | GGUF | — | — | — | featherless-ai-quants | 0 | 2.2k |
| netcat420/DEFUNCT-EXPERIMENT2_2 | merge | — | 7.62B | M | — | netcat420 | 0 | 1.7k |
| MInference/qwen25-math-7b-instruct | finetune | — | 7.62B | M | apache-2.0 | MInference | 1 | 1.6k |
| Satori-reasoning/Satori-7B-Round2 | finetune | — | 7.62B | M | apache-2.0 | Satori-reasoning | 11 | 1k |
| sravanthib/Qwen-2.5-7B-Simple-RL | finetune | — | 7.62B | M | — | sravanthib | 0 | 1.4k |
| TIGER-Lab/Qwen2.5-Math-7B-CFT | finetune | — | 7.62B | M | apache-2.0 | TIGER-Lab | 8 | 1k |
| Elliott/LUFFY-Qwen-Math-7B-Zero | finetune | — | 7.62B | M | mit | Elliott | 1 | 1.3k |
| Dongwei/Qwen-2.5-7B_Base_Math_smalllr | finetune | — | 7.62B | M | — | Dongwei | 6 | 893 |
| hkust-nlp/Qwen-2.5-Math-7B-SimpleRL | finetune | — | 7.62B | M | apache-2.0 | hkust-nlp | 4 | 873 |
| zwhe99/DeepMath-Zero-Math-7B | finetune | — | 7.62B | M | mit | zwhe99 | 4 | 673 |
| billwang37/optim-ai-7b-v1 | adapter | — | 7.62B | M | apache-2.0 | billwang37 | 0 | 811 |
| zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-2 | finetune | — | 7.62B | M | apache-2.0 | zbeeb | 0 | 611 |
| SunnyLin/Qwen2.5-7B-DPO-VP | finetune | — | 7.62B | M | — | SunnyLin | 2 | 470 |
| bunnycore/Qwen2.5-7B-Matrix | merge | — | 7.62B | M | — | bunnycore | 5 | 286 |
| Date | Commit | SHA |
|---|---|---|
| 2024-09-23 | Update README.md | b101308 |
| 2024-09-20 | Upload ./tokenizer_config.json with huggingface_hub | 8daf1d6 |
| 2024-09-19 | Upload ./tokenizer_config.json with huggingface_hub | 49db7ad |
| 2024-09-18 | Update README.md | 1dcca43 |
| 2024-09-18 | Update README.md | c720a84 |
| 2024-09-18 | Create LICENSE | 16c3b75 |
| 2024-09-18 | Create README.md | 5f4bbc4 |
| 2024-09-17 | Update tokenizer_config.json | 03004f9 |
| 2024-09-16 | Upload folder using huggingface_hub | 8269fff |
| 2024-09-16 | initial commit | abad3d2 |
Hosted endpoints observed for Qwen2.5-Math-7B, 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-Math-7B | — | — | — | — | — | — | — | 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 21:38 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:09 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.
