Qwen2.5-Coder-32B-Instruct
Qwen- Arena score
- 1230
- Among open models
- #105of 148
- Among all on Arena
- #306
- Votes
- 5,432
Measured on Qwen2.5-Coder-32B-Instruct, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Coding1276#95#281873
- Hard prompts, English1269#98#283759
- Software & IT1261#100#2951.4K
- Legal & government1257#99#291273
- Hard prompts1251#100#2901.4K
- Long prompts1251#98#294804
- Math1251#93#281725
- English1248#105#3072.7K
- Applied math1243#97#288619
- Russian1228#100#297822
- Business & finance1224#101#294629
- Instructions1223#102#3002.2K
- Multi-turn1222#104#3061K
- Chinese1222#96#297528
- Science1221#107#316956
- Expert1220#99#283267
- Non-English1205#106#3122.8K
- Writing & literature1191#110#3261.5K
- Medicine & health1186#107#311221
- Creative writing1174#111#325836
- Media & sports1150#111#330929
- Excluding ties1126#105#3063.4K
| Model | Params | Score |
|---|---|---|
| 7.6B | — | |
| 14.8B | — | |
| 32.8B | 1230 |
About as strong, smaller
Compare
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B

gemma-3n-E4B-itGoogle13067.8B

Molmo2-8BAi212878.7B
Discussion
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioQwen/Qwen2.5-Coder-32B-Instruct-GGUF71 builds
- MLX · Apple silicon: mlx-lm, LM Studiolmstudio-community/Qwen2.5-Coder-32B-Instruct-MLX-4bit23 builds
- AWQ · vLLM, SGLangQwen/Qwen2.5-Coder-32B-Instruct-AWQ4 builds
- GPTQ · vLLM, SGLangQwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int86 builds
Most downloaded
- Qwen2.5-Coder-32B-Instruct-AWQQwen · Quantization847K downloads
- Qwen2.5-Coder-32B-Instruct-GGUFQwen · Quantization69.8K downloads
- Qwen2.5-Coder-32B-Instruct-MLX-4bitlmstudio-community · Quantization40.2K downloads
- Qwen2.5-Coder-32B-Instruct-GGUFbartowski · Quantization38.6K downloads
- Qwen2.5-Coder-32B-Instruct-MLX-8bitlmstudio-community · Quantization37.1K downloads
BenchClub runs
Not runnable yet
Runs open once a Qwen2.5-Coder-32B-Instruct build is registered.
More from Qwen
See more
Qwen3.8-27B6.9M27.8B

Qwen3.5-27B1.7M27.8B

Qwen3.5-35B-A3B1.4M36.0B

Qwen3.5-122B-A10B775.1K125B
Other 20–40B models
See more
gemma-4-31B-itGoogle6.3M31.3B
Ornith-1.0-35BOrnith1.4M35.1B
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1.3M31.6B
GLM-4.7-FlashZ.ai1.2M31.2B