Skip to content
Weights Not Walls
Menu

Qwen

QwQ-32B-Preview

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
27 Nov 2024the date the repo was created
Context length
32k tokensfrom the model's config
Fine-tune
of Qwen/Qwen2.5-32B-InstructQwen2ForCausalLM
On Hugging Face
Qwen/QwQ-32B-Preview12k downloads in the last 30 days, 1.7k likes

Scores

1 independent result on 1 eval set
LiveBenchReported

Epoch's name: QwQ-32B-Preview. 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-Preview), 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

bartowski/QwQ-32B-Preview-GGUF (converted by bartowski), 8.8k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
IQ3_XS12.8 GBfile size15.3 GB12.8 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:IQ3_XS
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:IQ3_XS
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-IQ3_XS.gguf" --local-dir QwQ-32B-Preview-GGUF
Q3_K_S13.4 GBfile size15.9 GB13.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q3_K_S
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q3_K_S
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q3_K_S.gguf" --local-dir QwQ-32B-Preview-GGUF
IQ3_M13.8 GBfile size16.3 GB13.8 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:IQ3_M
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:IQ3_M
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-IQ3_M.gguf" --local-dir QwQ-32B-Preview-GGUF
Q3_K_M14.8 GBfile size17.3 GB14.8 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q3_K_M
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q3_K_M
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q3_K_M.gguf" --local-dir QwQ-32B-Preview-GGUF
Q3_K_L16.1 GBfile size18.6 GB16.1 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q3_K_L
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q3_K_L
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q3_K_L.gguf" --local-dir QwQ-32B-Preview-GGUF
IQ4_XS16.5 GBfile size19.0 GB16.5 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:IQ4_XS
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:IQ4_XS
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-IQ4_XS.gguf" --local-dir QwQ-32B-Preview-GGUF
Q3_K_XL16.7 GBfile size19.2 GB16.7 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q3_K_XL
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q3_K_XL
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q3_K_XL.gguf" --local-dir QwQ-32B-Preview-GGUF
Q4_0_4_417.4 GBfile size19.9 GB17.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q4_0_4_4
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q4_0_4_4
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q4_0_4_4.gguf" --local-dir QwQ-32B-Preview-GGUF
Q4_0_4_817.4 GBfile size19.9 GB17.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q4_0_4_8
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q4_0_4_8
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q4_0_4_8.gguf" --local-dir QwQ-32B-Preview-GGUF
Q4_0_8_817.4 GBfile size19.9 GB17.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q4_0_8_8
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q4_0_8_8
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q4_0_8_8.gguf" --local-dir QwQ-32B-Preview-GGUF
IQ4_NL17.4 GBfile size19.9 GB17.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:IQ4_NL
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:IQ4_NL
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-IQ4_NL.gguf" --local-dir QwQ-32B-Preview-GGUF
Q4_017.4 GBfile size19.9 GB17.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q4_0
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q4_0
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q4_0.gguf" --local-dir QwQ-32B-Preview-GGUF
Q4_K_S17.5 GBfile size20.0 GB17.5 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q4_K_S
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q4_K_S
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q4_K_S.gguf" --local-dir QwQ-32B-Preview-GGUF
Q4_K_M18.5 GBfile size21.0 GB18.5 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q4_K_M
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q4_K_M
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q4_K_M.gguf" --local-dir QwQ-32B-Preview-GGUF
Q4_K_L19.0 GBfile size21.5 GB19.0 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q4_K_L
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q4_K_L
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q4_K_L.gguf" --local-dir QwQ-32B-Preview-GGUF
Q5_K_S21.1 GBfile size23.6 GB21.1 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q5_K_S
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q5_K_S
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q5_K_S.gguf" --local-dir QwQ-32B-Preview-GGUF
Q5_K_M21.7 GBfile size24.2 GB21.7 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q5_K_M
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q5_K_M
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q5_K_M.gguf" --local-dir QwQ-32B-Preview-GGUF
Q5_K_L22.1 GBfile size24.6 GB22.1 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q5_K_L
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q5_K_L
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q5_K_L.gguf" --local-dir QwQ-32B-Preview-GGUF
Q6_K25.0 GBfile size27.5 GB25.0 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q6_K
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q6_K
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q6_K.gguf" --local-dir QwQ-32B-Preview-GGUF
Q6_K_L25.4 GBfile size27.9 GB25.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q6_K_L
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q6_K_L
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q6_K_L.gguf" --local-dir QwQ-32B-Preview-GGUF
Q8_032.4 GBfile size34.9 GB32.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:Q8_0
Ollama
ollama run hf.co/bartowski/QwQ-32B-Preview-GGUF:Q8_0
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-Q8_0.gguf" --local-dir QwQ-32B-Preview-GGUF
BF1661.0 GBfile size, 2 parts63.5 GB61.0 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/QwQ-32B-Preview-GGUF:BF16
Download
hf download bartowski/QwQ-32B-Preview-GGUF --include "QwQ-32B-Preview-bf16/QwQ-32B-Preview-bf16-*-of-00002.gguf" --local-dir QwQ-32B-Preview-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 6bitmlx-community/QwQ-32B-Preview-6bit24.8 GBfile size27.3 GB24.8 + 2.0 + 0.50Download page
MLX 8bitmlx-community/Qwen_QwQ-32B-Preview_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-Preview --local-dir QwQ-32B-Preview
Other conversions (18; 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.