General model by typhoon-ai · 30.53B parameters
typhoon2.5 qwen3 30b a3b can run but will be tight at 84% of RAM. Consider a lower quantization or closing other apps.
~87 tok/s
Q4_K_M · 20.2 GB
Alternative: Q3_K_M (17.2 GB, ~105 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 34.6 GB | ~48 tok/s | ✗ |
| Q6_K | 26.9 GB | ~63 tok/s | ✗ |
| Q5_K_M | 23.3 GB | ~74 tok/s | ✗ |
| Q4_K_M Recommended | 20.2 GB | ~87 tok/s | ✓ |
| Q3_K_M | 17.2 GB | ~105 tok/s | ✓ |
| Q2_K | 13.8 GB | ~137 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free