General model by arcee-ai · 26.12B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Trinity Mini can run but will be tight at 83% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q5_K_M · 20.0 GB · Benchmark needed
Alternative: Q4_K_M (17.4 GB, ~102 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 29.6 GB | ~56 tok/s | ✗ |
| Q6_K | 23.1 GB | ~74 tok/s | ✗ |
| Q5_K_M Recommended | 20.0 GB | ~87 tok/s | ✓ |
| Q4_K_M | 17.4 GB | ~102 tok/s | ✓ |
| Q3_K_M | 14.7 GB | ~123 tok/s | ✓ |
| Q2_K | 11.9 GB | ~160 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