bartowski
Qwen2.5 Coder 32B Instruct
Qwen2.5 Coder 32B Instruct is a 32.8B dense qwen2 model from bartowski. Configured context length is 32,768 tokens. License: apache-2.0. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters32.8B
Context32K
Attentiongqa
Licenseapache-2.0
64 layers · 8 KV heads · head dim 128 · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| Q8_0 | 32.4 GB | Hugging Face file bytes |
| Q6_K | 50.4 GB | Hugging Face file bytes |
| Q5_K_M | 21.7 GB | Hugging Face file bytes |
| Q5_K_S | 21.1 GB | Hugging Face file bytes |
| Q4_K_M | 18.5 GB | Hugging Face file bytes |
| Q4_K_S | 17.5 GB | Hugging Face file bytes |
| IQ4_NL | 17.4 GB | Hugging Face file bytes |
| IQ4_XS | 16.5 GB | Hugging Face file bytes |
| Q4_0 | 69.5 GB | Hugging Face file bytes |
| Q3_K_L | 16.1 GB | Hugging Face file bytes |
| Q3_K_M | 14.8 GB | Hugging Face file bytes |
| IQ3_M | 13.8 GB | Hugging Face file bytes |
| Q3_K_S | 13.4 GB | Hugging Face file bytes |
| IQ3_XXS | 12.0 GB | Hugging Face file bytes |
| Q2_K | 23.6 GB | Hugging Face file bytes |
| IQ2_S | 9.67 GB | Hugging Face file bytes |
| IQ2_XXS | 8.41 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Partial offload | Q4_K_M | 3.1–4.2 |
| GeForce RTX 3060 12GB | Tight fit | IQ2_XXS | 20–27 |
| GeForce RTX 4060 Ti 16GB | Tight fit | IQ3_XXS | 11–14 |
| GeForce RTX 4090 | Tight fit | Q4_K_M | 25–34 |
| GeForce RTX 5090 | Runs | Q5_K_M | 39–53 |
| Apple M4 Pro | Tight fit | Q3_K_L | 8.2–11 |
| Apple M5 | Tight fit | IQ2_XXS | 8.3–11 |
| CPU only · DDR5-5600 | Runs on CPU | Q5_K_M | 1.9–2.6 |
Smallest devices that fit it fully
- GeForce RTX 2080 Ti — Tight fit, IQ2_XXS, 35–48 tok/s
- GeForce GTX 1080 Ti — Tight fit, IQ2_XXS, 28–38 tok/s
- GeForce RTX 5070 — Tight fit, IQ2_XXS, 37–50 tok/s
- GeForce RTX 4070 Ti — Tight fit, IQ2_XXS, 27–37 tok/s
- GeForce RTX 4070 Super — Tight fit, IQ2_XXS, 27–37 tok/s
- GeForce RTX 4070 — Tight fit, IQ2_XXS, 27–37 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (IQ3_XXS).
llama.cpp
llama-server -hf bartowski/Qwen2.5-Coder-32B-Instruct-GGUF:IQ3_XXS -c 8192 -ngl 64
Ollama
ollama run qwen2.5
LM Studio
lms get bartowski/Qwen2.5-Coder-32B-Instruct-GGUF # Then load quant IQ3_XXS