General model by cyankiwi · 24.27B parameters
Qwen3.5 122B A10B AWQ 4bit can run but will be tight at 77% of RAM. Consider a lower quantization or closing other apps.
~128 tok/s
Q5_K_M · 18.6 GB
Alternative: Q4_K_M (16.2 GB, ~151 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 27.6 GB | ~83 tok/s | ✗ |
| Q6_K | 21.5 GB | ~109 tok/s | ✗ |
| Q5_K_M Recommended | 18.6 GB | ~128 tok/s | ✓ |
| Q4_K_M | 16.2 GB | ~151 tok/s | ✓ |
| Q3_K_M | 13.7 GB | ~182 tok/s | ✓ |
| Q2_K | 11.1 GB | ~236 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free