- Size
- 72.7B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, Qwen License AgreementOur reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 16 Sep 2024the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Fine-tune
- of Qwen/Qwen2.5-72BQwen2ForCausalLM
- On Hugging Face
- Qwen/Qwen2.5-72B-Instruct156k downloads in the last 30 days, 1.0k likes
Scores
- default setting49.1%±2.727 Jan 2025, log
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting63.2%±1.127 Jan 2025, log
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: gpt-5-2025-08-07_high, 98.1% (OpenAI). All 108 results
- default setting8.1%±2.625 Feb 2025, log
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- default setting16.2%±1.625 Nov 2024, balrogai.com
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: gpt-6-astra_max, 68.3% (OpenAI). All 41 results
- default setting62.9%conceptualreasoning.ai
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- default setting13.4%8.4 to 18.5conceptualreasoning.ai
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- default setting35.8%METR - Measuring AI Ability to Complete Long Tasks
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: claude-mythos-preview-early, 85.2% (Anthropic). All 49 results
- Shots: 585.3%Phi-4 Technical Report
- Shots: 583.4%Stanford CRFM Leaderboard
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
- Environment model: Claude 3.5 Sonnet5.7%17 Dec 2024, TheAgentCompany experiment results github
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: gemini-2.5-flash-preview-09-2025, 41.1% (Google DeepMind). All 16 results
- default setting16.0%±0.0WeirdML Leaderboard, via Epoch AI
Epoch's name: qwen2.5-72b-instruct. Best closed model on this set: gpt-6-astra_promax, 93.6% (OpenAI). All 173 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.5 GB, worked out from the model's config (Qwen/Qwen2.5-72B-Instruct), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
Qwen/Qwen2.5-72B-Instruct-GGUF (the maker's own conversion), 12k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 25.5 GBfile size, 7 parts | 28.5 GB25.5 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:Q2_KDownload hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-q2_k-*-of-00007.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
| Q3_K_M | 33.0 GBfile size, 9 parts | 36.0 GB33.0 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:Q3_K_MDownload hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-q3_k_m-*-of-00009.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
| Q4_0 | 38.5 GBfile size, 11 parts | 41.5 GB38.5 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:Q4_0Download hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-q4_0-*-of-00011.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
| Q4_K_M | 41.0 GBfile size, 12 parts | 44.0 GB41.0 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:Q4_K_MDownload hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-q4_k_m-*-of-00012.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
| Q5_0 | 46.9 GBfile size, 13 parts | 49.9 GB46.9 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:Q5_0Download hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-q5_0-*-of-00013.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
| Q5_K_M | 48.1 GBfile size, 14 parts | 51.1 GB48.1 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:Q5_K_MDownload hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-q5_k_m-*-of-00014.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
| Q6_K | 55.7 GBfile size, 16 parts | 58.7 GB55.7 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:Q6_KDownload hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-q6_k-*-of-00016.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
| Q8_0 | 72.2 GBfile size, 21 parts | 75.2 GB72.2 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:Q8_0Download hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-q8_0-*-of-00021.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
| F16 | 135.9 GBfile size, 42 parts | 138.9 GB135.9 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-72B-Instruct-GGUF:F16Download hf download Qwen/Qwen2.5-72B-Instruct-GGUF --include "qwen2.5-72b-instruct-fp16-*-of-00042.gguf" --local-dir Qwen2.5-72B-Instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 3bitmlx-community/Qwen2.5-72B-Instruct-3bit | 29.6 GBfile size | 32.6 GB29.6 + 2.5 + 0.50 | Download page |
| MLX 4bitmlx-community/Qwen2.5-72B-Instruct-4bit | 38.1 GBfile size | 41.1 GB38.1 + 2.5 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 135.4 GBfile size | 138.4 GB135.4 + 2.5 + 0.50 |
hf download Qwen/Qwen2.5-72B-Instruct --local-dir Qwen2.5-72B-InstructOther conversions (22; sizes not read)
- Qwen/Qwen2.5-72B-Instruct-AWQ AWQ, by the maker, 140k downloads
- Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4 GPTQ, int4, by the maker, 6.8k downloads
- Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8 GPTQ, int8, by the maker, 945 downloads
- unsloth/Qwen2.5-72B-Instruct-bnb-4bit bitsandbytes, 4bit, 1.5k downloads
- enfuse/Qwen2.5-72B-Instruct-NVFP4 NVFP4, 701 downloads
- axana-labs/Qwen2.5-72B-Instruct-bnb-4bit bitsandbytes, 4bit, 359 downloads
- mesolitica/Qwen2.5-72B-Instruct-FP8 FP8, 87 downloads
- tclf90/qwen2.5-72b-instruct-gptq-int3 GPTQ, 82 downloads
- tclf90/qwen2.5-72b-instruct-gptq-int4 GPTQ, int4, 80 downloads
- VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-256-woft Other, 27 downloads
- rkayaith/Qwen2.5-72B-Instruct-fp8-block FP8, 23 downloads
- bartowski/Qwen2.5-72B-Instruct-exl2 EXL2, 20 downloads
- mlc-ai/Qwen2.5-72B-Instruct-q4f16_1-MLC Other, 19 downloads
- OPEA/Qwen2.5-72B-Instruct-int2-sym-inc Other, 19 downloads
- ig1/Qwen2.5-72B-Instruct-FP8-Dynamic FP8, 16 downloads
- VPTQ-community/Qwen2.5-72B-Instruct-v8-k1024-512-woft Other, 14 downloads
- kimleang123/Qwen2.5-72B-Instruct-bnb bitsandbytes, 12 downloads
- Gensyn/Qwen2.5-72B-Instruct-bnb-4bit bitsandbytes, 4bit, 11 downloads
- ark4004/Qwen2.5-72B-Instruct-AWQ-JH AWQ, 11 downloads
- Dracones/Qwen2.5-72B-Instruct_exl2_3.5bpw EXL2, 7 downloads
- Dracones/Qwen2.5-72B-Instruct_exl2_3.0bpw EXL2, 7 downloads
- Dracones/Qwen2.5-72B-Instruct_exl2_7.0bpw EXL2, 6 downloads
The Hub tags 97 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
2 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| DeepInfra | $0.36 | $0.40 | 32k | fp8 | 43 | 0.2 s | 98.2% | yes | yes |
| featherless-ai | ? | ? | ? | not given | ? | ? | ? | not given | not given |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "Qwen/Qwen2.5-72B-Instruct:deepinfra", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- Sao10K/72B-Qwen2.5-Kunou-v172.7B18kUnreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.