General model by ibivibiv · 35.43B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
multimaster 7b v6 can run but will be tight at 83% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q3_K_M · 19.8 GB · Benchmark needed
Alternative: Q2_K (15.9 GB, ~35 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 40.0 GB | ~12 tok/s | ✗ |
| Q6_K | 31.2 GB | ~16 tok/s | ✗ |
| Q5_K_M | 26.9 GB | ~19 tok/s | ✗ |
| Q4_K_M | 23.4 GB | ~22 tok/s | ✗ |
| Q3_K_M Recommended | 19.8 GB | ~27 tok/s | ✓ |
| Q2_K | 15.9 GB | ~35 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