Skip to content
Weights Not Walls
Menu

Qwen

QwQ-32B

Reviewed
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
5 Mar 2025the date the repo was created
Context length
40k tokensfrom the model's config
Fine-tune
of Qwen/Qwen2.5-32BQwen2ForCausalLM
On Hugging Face
Qwen/QwQ-32B30k downloads in the last 30 days, 3.0k likes

Scores

6 independent results on 6 eval sets
GPQA diamondRe-run by Epoch AI
  • default setting65.3%±2.828 Aug 2026, log

Epoch's name: QwQ-32B. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results

OTIS Mock AIME 2024-2025Re-run by Epoch AI
  • default setting59.2%±6.328 Aug 2026, log

Epoch's name: QwQ-32B. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results

Epoch's name: QwQ-32B. Best closed model on this set: gpt-5-2025-08-07_high, 88.0% (OpenAI). All 72 results

Epoch's name: chutes/QwQ-32B. Best closed model on this set: gpt-5-2025-08-07_medium, 97.2% (OpenAI). All 61 results

Epoch's name: QwQ-32B (16K thinking). Best closed model on this set: gpt-5-2025-08-07_medium, 86.0% (OpenAI). All 49 results

LiveBenchReported

Epoch's name: QwQ-32B. Best closed model on this set: gemini-2.5-pro-exp-03-25, 82.3% (Google DeepMind). All 54 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

file sizes read from the Hub 19 Nov 2026

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/QwQ-32B), 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/QwQ-32B-GGUF (the maker's own conversion), 20k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q4_K_M18.5 GBfile size21.0 GB18.5 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/QwQ-32B-GGUF:Q4_K_M
Ollama
ollama run hf.co/Qwen/QwQ-32B-GGUF:Q4_K_M
Download
hf download Qwen/QwQ-32B-GGUF --include "qwq-32b-q4_k_m.gguf" --local-dir QwQ-32B-GGUF
Q5_021.1 GBfile size23.6 GB21.1 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/QwQ-32B-GGUF:Q5_0
Ollama
ollama run hf.co/Qwen/QwQ-32B-GGUF:Q5_0
Download
hf download Qwen/QwQ-32B-GGUF --include "qwq-32b-q5_0.gguf" --local-dir QwQ-32B-GGUF
Q5_K_M21.7 GBfile size24.2 GB21.7 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/QwQ-32B-GGUF:Q5_K_M
Ollama
ollama run hf.co/Qwen/QwQ-32B-GGUF:Q5_K_M
Download
hf download Qwen/QwQ-32B-GGUF --include "qwq-32b-q5_k_m.gguf" --local-dir QwQ-32B-GGUF
Q6_K25.0 GBfile size27.5 GB25.0 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/QwQ-32B-GGUF:Q6_K
Ollama
ollama run hf.co/Qwen/QwQ-32B-GGUF:Q6_K
Download
hf download Qwen/QwQ-32B-GGUF --include "qwq-32b-q6_k.gguf" --local-dir QwQ-32B-GGUF
Q8_032.4 GBfile size34.9 GB32.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/QwQ-32B-GGUF:Q8_0
Ollama
ollama run hf.co/Qwen/QwQ-32B-GGUF:Q8_0
Download
hf download Qwen/QwQ-32B-GGUF --include "qwq-32b-q8_0.gguf" --local-dir QwQ-32B-GGUF
F1661.0 GBfile size, 17 parts63.5 GB61.0 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/QwQ-32B-GGUF:F16
Download
hf download Qwen/QwQ-32B-GGUF --include "fp16/qwq-32b-fp16-*-of-00017.gguf" --local-dir QwQ-32B-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitmlx-community/QwQ-32B-4bit17.2 GBfile size19.7 GB17.2 + 2.0 + 0.50Download page
MLX 8bitlmstudio-community/QwQ-32B-MLX-8bit32.4 GBfile size34.9 GB32.4 + 2.0 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights61.0 GBfile size63.5 GB61.0 + 2.0 + 0.50
hf download Qwen/QwQ-32B --local-dir QwQ-32B
Other conversions (23; sizes not read)

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

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

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.

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.