General model by aidc-ai · 31.38B parameters
Ovis2.6 30B A3B can run but will be tight at 73% of RAM. Consider a lower quantization or closing other apps.
~102 tok/s
Q3_K_M · 17.6 GB
Alternative: Q2_K (14.2 GB, ~133 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 35.5 GB | ~47 tok/s | ✗ |
| Q6_K | 27.7 GB | ~61 tok/s | ✗ |
| Q5_K_M | 23.9 GB | ~72 tok/s | ✗ |
| Q4_K_M | 20.8 GB | ~85 tok/s | ✗ |
| Q3_K_M Recommended | 17.6 GB | ~102 tok/s | ✓ |
| Q2_K | 14.2 GB | ~133 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free