General model by facebook · 29.96B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
opt 30b can run but will be tight at 83% of RAM. Consider a lower quantization or closing other apps.
~10 tok/s
Q4_K_M · 19.8 GB · Estimated
Alternative: Q3_K_M (16.8 GB, ~12 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 33.9 GB | ~5 tok/s | ✗ |
| Q6_K | 26.4 GB | ~7 tok/s | ✗ |
| Q5_K_M | 22.8 GB | ~8 tok/s | ✗ |
| Q4_K_M Recommended | 19.8 GB | ~10 tok/s | ✓ |
| Q3_K_M | 16.8 GB | ~12 tok/s | ✓ |
| Q2_K | 13.5 GB | ~15 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free