Qwen
Qwen2.5 32B
Qwen2.5 32B is an open-weights 32B-parameter model by Qwen. It is listed as in-progress on the local.ai leaderboard.
open weights
Parameters
32B
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2024-09-25
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Q4_K_M 18.6GQ6_K 28.8GQ8_0 35.2GFP16 64G| Quantization | ≈ File size | Note |
|---|---|---|
| IQ2_XXS | 8.6 GB | Extreme compression, largest quality loss |
| IQ3_XXS | 11.5 GB | Very small |
| Q3_K_M | 14.7 GB | Small |
| NVFP4 | 16 GB | NVIDIA 4-bit |
| Q4_K_S | 17.3 GB | Common |
| Q4_K_M | 18.6 GB | Most common sweet spot |
| Q5_K_M | 24.3 GB | Balanced |
| Q6_K | 28.8 GB | Near-lossless |
| Q8_0 | 35.2 GB | Near-lossless |
| FP16 | 64 GB | Original weights |
Actual files on HuggingFace
| File | Size |
|---|---|
| model-00001-of-00017.safetensors | 3.65 GB |
| model-00004-of-00017.safetensors | 3.63 GB |
| model-00005-of-00017.safetensors | 3.63 GB |
| model-00006-of-00017.safetensors | 3.63 GB |
| model-00007-of-00017.safetensors | 3.63 GB |
| model-00008-of-00017.safetensors | 3.63 GB |
GGUF: bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · 116,966 downloads
| File | Size | |
|---|---|---|
| Qwen2.5-Coder-32B-Instruct-IQ2_M.gguf | 10.49 GB | download |
| Qwen2.5-Coder-32B-Instruct-IQ2_S.gguf | 9.67 GB | download |
| Qwen2.5-Coder-32B-Instruct-IQ2_XS.gguf | 9.27 GB | download |
| Qwen2.5-Coder-32B-Instruct-IQ2_XXS.gguf | 8.41 GB | download |
| Qwen2.5-Coder-32B-Instruct-IQ3_M.gguf | 13.79 GB | download |
| Qwen2.5-Coder-32B-Instruct-IQ3_XS.gguf | 12.76 GB | download |
| Qwen2.5-Coder-32B-Instruct-IQ3_XXS.gguf | 11.96 GB | download |
| Qwen2.5-Coder-32B-Instruct-IQ4_NL.gguf | 17.40 GB | download |
| Qwen2.5-Coder-32B-Instruct-IQ4_XS.gguf | 16.48 GB | download |
| Qwen2.5-Coder-32B-Instruct-Q2_K.gguf | 11.47 GB | download |
| Qwen2.5-Coder-32B-Instruct-Q2_K_L.gguf | 12.18 GB | download |
| Qwen2.5-Coder-32B-Instruct-Q3_K_L.gguf | 16.06 GB | download |
GGUF: Qwen/Qwen2.5-Coder-32B-Instruct-GGUF · 73,095 downloads
| File | Size | |
|---|---|---|
| qwen2.5-coder-32b-instruct-fp16-00001-of-00009.gguf | 7.29 GB | download |
| qwen2.5-coder-32b-instruct-fp16-00002-of-00009.gguf | 7.27 GB | download |
| qwen2.5-coder-32b-instruct-fp16-00003-of-00009.gguf | 7.27 GB | download |
| qwen2.5-coder-32b-instruct-fp16-00004-of-00009.gguf | 7.27 GB | download |
| qwen2.5-coder-32b-instruct-fp16-00005-of-00009.gguf | 7.27 GB | download |
| qwen2.5-coder-32b-instruct-fp16-00006-of-00009.gguf | 7.27 GB | download |
| qwen2.5-coder-32b-instruct-fp16-00007-of-00009.gguf | 7.27 GB | download |
| qwen2.5-coder-32b-instruct-fp16-00008-of-00009.gguf | 7.27 GB | download |
| qwen2.5-coder-32b-instruct-fp16-00009-of-00009.gguf | 2.89 GB | download |
| qwen2.5-coder-32b-instruct-q2_k-00001-of-00002.gguf | 7.44 GB | download |
| qwen2.5-coder-32b-instruct-q2_k-00002-of-00002.gguf | 4.03 GB | download |
| qwen2.5-coder-32b-instruct-q2_k.gguf | 11.47 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.