Chat model by Alibaba · 32.76B parameters
Qwen2.5 32B Instruct AWQ can run but will be tight at 77% of RAM. Consider a lower quantization or closing other apps.
~11 tok/s
Q3_K_M · 18.4 GB
Alternative: Q2_K (14.8 GB, ~14 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 37.0 GB | ~5 tok/s | ✗ |
| Q6_K | 28.9 GB | ~6 tok/s | ✗ |
| Q5_K_M | 24.9 GB | ~8 tok/s | ✗ |
| Q4_K_M | 21.6 GB | ~9 tok/s | ✗ |
| Q3_K_M Recommended | 18.4 GB | ~11 tok/s | ✓ |
| Q2_K | 14.8 GB | ~14 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free