Chat model by Alibaba · 33.45B parameters
Qwen2.5 VL 32B Instruct can run but will be tight at 78% of RAM. Consider a lower quantization or closing other apps.
~11 tok/s
Q3_K_M · 18.7 GB
Alternative: Q2_K (15.1 GB, ~14 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 37.8 GB | ~5 tok/s | ✗ |
| Q6_K | 29.5 GB | ~6 tok/s | ✗ |
| Q5_K_M | 25.4 GB | ~7 tok/s | ✗ |
| Q4_K_M | 22.1 GB | ~9 tok/s | ✗ |
| Q3_K_M Recommended | 18.7 GB | ~11 tok/s | ✓ |
| Q2_K | 15.1 GB | ~14 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free