Qwen2.5-32B-Instruct
QwenLMArena
Not ranked on LMArena
LMArena only ranks the models it serves.
| Model | Params | Score |
|---|---|---|
| 494M | — | |
| 494M | — | |
| 1.5B | — | |
| 3.1B | — | |
| 7.6B | — | |
| 32.8B | — | |
| 72.7B | 1269 |
Discussion
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiobartowski/Qwen2.5-32B-Instruct-GGUF68 builds
- MLX · Apple silicon: mlx-lm, LM Studiolmstudio-community/Qwen2.5-32B-Instruct-MLX-4bit9 builds
- AWQ · vLLM, SGLangQwen/Qwen2.5-32B-Instruct-AWQ7 builds
- GPTQ · vLLM, SGLangQwen/Qwen2.5-32B-Instruct-GPTQ-Int43 builds
Most downloaded
- Qwen2.5-32B-Instruct-AWQQwen · Quantization991.4K downloads
- Qwen2.5-32B-Instruct-GGUFbartowski · Quantization594.3K downloads
- Qwen2.5-32B-Instruct-GPTQ-Int4Qwen · Quantization380.4K downloads
- Qwen2.5-32B-Instruct-GPTQ-Int8Qwen · Quantization98.4K downloads
- Qwen2.5-32B-Instruct-bnb-4bitunsloth · Quantization50.5K downloads
BenchClub runs
Not runnable yet
Runs open once a Qwen2.5-32B-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