- Size
- 32.8B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, Apache License 2.0Our 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
- 17 Sep 2024the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Fine-tune
- of Qwen/Qwen2.5-32BQwen2ForCausalLM
- On Hugging Face
- Qwen/Qwen2.5-32B-Instruct680k downloads in the last 30 days, 378 likes
Scores
- default setting46.1%±2.630 Jan 2025, log
Epoch's name: qwen2.5-32b-instruct. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting56.1%±1.130 Jan 2025, log
Epoch's name: qwen2.5-32b-instruct. Best closed model on this set: gpt-5-2025-08-07_high, 98.1% (OpenAI). All 108 results
- default setting7.4%±2.125 Feb 2025, log
Epoch's name: qwen2.5-32b-instruct. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 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: 2.0 GB, worked out from the model's config (Qwen/Qwen2.5-32B-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/Qwen2.5-32B-Instruct-GGUF (the maker's own conversion), 9.1k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 11.5 GBfile size, 4 parts | 14.0 GB11.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:Q2_KDownload hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-q2_k-*-of-00004.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
| Q3_K_M | 14.8 GBfile size, 5 parts | 17.3 GB14.8 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:Q3_K_MDownload hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-q3_k_m-*-of-00005.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
| Q4_0 | 17.4 GBfile size, 5 parts | 19.9 GB17.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:Q4_0Download hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-q4_0-*-of-00005.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
| Q4_K_M | 18.5 GBfile size, 5 parts | 21.0 GB18.5 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:Q4_K_MDownload hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-q4_k_m-*-of-00005.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
| Q5_0 | 21.1 GBfile size, 6 parts | 23.6 GB21.1 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:Q5_0Download hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-q5_0-*-of-00006.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
| Q5_K_M | 21.7 GBfile size, 6 parts | 24.2 GB21.7 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:Q5_K_MDownload hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-q5_k_m-*-of-00006.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
| Q6_K | 25.0 GBfile size, 7 parts | 27.5 GB25.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:Q6_KDownload hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-q6_k-*-of-00007.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
| Q8_0 | 32.4 GBfile size, 9 parts | 34.9 GB32.4 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:Q8_0Download hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-q8_0-*-of-00009.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
| F16 | 61.0 GBfile size, 17 parts | 63.5 GB61.0 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-32B-Instruct-GGUF:F16Download hf download Qwen/Qwen2.5-32B-Instruct-GGUF --include "qwen2.5-32b-instruct-fp16-*-of-00017.gguf" --local-dir Qwen2.5-32B-Instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitlmstudio-community/Qwen2.5-32B-Instruct-MLX-4bit | 17.2 GBfile size | 19.7 GB17.2 + 2.0 + 0.50 | Download page |
| MLX 8bitlmstudio-community/Qwen2.5-32B-Instruct-MLX-8bit | 32.4 GBfile size | 34.9 GB32.4 + 2.0 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 61.0 GBfile size | 63.5 GB61.0 + 2.0 + 0.50 |
hf download Qwen/Qwen2.5-32B-Instruct --local-dir Qwen2.5-32B-InstructOther conversions (14; sizes not read)
- Qwen/Qwen2.5-32B-Instruct-AWQ AWQ, by the maker, 999k downloads
- Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4 GPTQ, int4, by the maker, 342k downloads
- Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8 GPTQ, int8, by the maker, 126k downloads
- unsloth/Qwen2.5-32B-Instruct-bnb-4bit bitsandbytes, 4bit, 51k downloads
- drawais/Qwen2.5-32B-Instruct-AWQ-INT4 AWQ, int4, 296 downloads
- positron-ai/Qwen_Qwen2.5-32B-Instruct-ingest-best-gptq GPTQ, 38 downloads
- mlc-ai/Qwen2.5-32B-Instruct-q4f16_1-MLC Other, 24 downloads
- nm-testing/Qwen2.5-32B-Instruct-FP8-dynamic FP8, 24 downloads
- OPEA/Qwen2.5-32B-Instruct-int4-sym-mixed-inc Other, int4, 23 downloads
- Dracones/Qwen2.5-32B-Instruct_exl2_4.5bpw EXL2, 21 downloads
- Dracones/Qwen2.5-32B-Instruct_exl2_7.0bpw EXL2, 20 downloads
- Dracones/Qwen2.5-32B-Instruct_exl2_4.0bpw EXL2, 20 downloads
- Dracones/Qwen2.5-32B-Instruct_exl2_8.0bpw EXL2, 19 downloads
- mlc-ai/Qwen2.5-32B-Instruct-q0f16-MLC Other, 15 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
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.
- Qwen/QwQ-32B-Preview32.8B12kReviewed
- nvidia/OpenCodeReasoning-Nemotron-32B32.8B777Unreviewed
- nvidia/OpenCodeReasoning-Nemotron-1.1-32B32.8B369Unreviewed
- nvidia/OpenCodeReasoning-Nemotron-32B-IOI32.8B293Unreviewed
- tencent/DRIVE-SFT32.8B151Unreviewed
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.