Skip to content
Weights Not Walls
Menu

Qwen

Qwen2.5-Coder-32B-Instruct

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
6 Nov 2024the date the repo was created
Context length
32k tokensfrom the model's config
Fine-tune
of Qwen/Qwen2.5-Coder-32BQwen2ForCausalLM
On Hugging Face
Qwen/Qwen2.5-Coder-32B-Instruct518k downloads in the last 30 days, 2.2k likes

Scores

4 independent results on 3 eval sets

Epoch's name: Qwen2.5-Coder-32B-Instruct. Best closed model on this set: gpt-5-2025-08-07_high, 88.0% (OpenAI). All 72 results

GSM8KReported

Epoch's name: Qwen2.5-Coder-32B-Instruct. Best closed model on this set: gpt-4-0314, 92.0% (OpenAI). All 170 results

LiveBenchReported

Epoch's name: Qwen2.5-Coder-32B-Instruct. 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/Qwen2.5-Coder-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-Coder-32B-Instruct-GGUF (the maker's own conversion), 70k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q2_K11.5 GBfile size, 2 parts14.0 GB11.5 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q2_K
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-q2_k-*-of-00002.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF
Q3_K_M14.8 GBfile size, 2 parts17.3 GB14.8 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q3_K_M
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-q3_k_m-*-of-00002.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF
Q4_017.4 GBfile size, 3 parts19.9 GB17.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q4_0
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-q4_0-*-of-00003.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF
Q4_K_M18.5 GBfile size, 3 parts21.0 GB18.5 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q4_K_M
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-q4_k_m-*-of-00003.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF
Q5_021.1 GBfile size, 3 parts23.6 GB21.1 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q5_0
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-q5_0-*-of-00003.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF
Q5_K_M21.7 GBfile size, 3 parts24.2 GB21.7 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q5_K_M
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-q5_k_m-*-of-00003.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF
Q6_K25.0 GBfile size, 4 parts27.5 GB25.0 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q6_K
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-q6_k-*-of-00004.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF
Q8_032.4 GBfile size, 5 parts34.9 GB32.4 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q8_0
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-q8_0-*-of-00005.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF
F1661.0 GBfile size, 9 parts63.5 GB61.0 + 2.0 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:F16
Download
hf download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF --include "qwen2.5-coder-32b-instruct-fp16-*-of-00009.gguf" --local-dir Qwen2.5-Coder-32B-Instruct-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitlmstudio-community/Qwen2.5-Coder-32B-Instruct-MLX-4bit17.2 GBfile size19.7 GB17.2 + 2.0 + 0.50Download page
MLX 8bitlmstudio-community/Qwen2.5-Coder-32B-Instruct-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/Qwen2.5-Coder-32B-Instruct --local-dir Qwen2.5-Coder-32B-Instruct
Other conversions (14; 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

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.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
Cloudflare$0.66$1.0032knot given321.8 s100.0%nono
featherless-ai???not given???not givennot 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-Coder-32B-Instruct:cloudflare", "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

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

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.