General model by hpcai-tech · 36.24B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
grok 1 can run but will be tight at 84% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q3_K_M · 20.3 GB · Benchmark needed
Alternative: Q2_K (16.3 GB, ~44 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 40.9 GB | ~15 tok/s | ✗ |
| Q6_K | 31.9 GB | ~20 tok/s | ✗ |
| Q5_K_M | 27.5 GB | ~24 tok/s | ✗ |
| Q4_K_M | 23.9 GB | ~28 tok/s | ✗ |
| Q3_K_M Recommended | 20.3 GB | ~34 tok/s | ✓ |
| Q2_K | 16.3 GB | ~44 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