Chat model by quanttrio · 31.07B parameters
Qwen3 VL 30B A3B Instruct AWQ can run but will be tight at 86% of RAM. Consider a lower quantization or closing other apps.
~118 tok/s
Q4_K_M · 20.6 GB
Alternative: Q3_K_M (17.4 GB, ~142 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 35.2 GB | ~65 tok/s | ✗ |
| Q6_K | 27.4 GB | ~85 tok/s | ✗ |
| Q5_K_M | 23.7 GB | ~100 tok/s | ✗ |
| Q4_K_M Recommended | 20.6 GB | ~118 tok/s | ✓ |
| Q3_K_M | 17.4 GB | ~142 tok/s | ✓ |
| Q2_K | 14.0 GB | ~184 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free