General model by bigscience · 13.95B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
mt0 xxl p3 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 67% of your RAM.
~12 tok/s
Q8_0 · 16.1 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 16.1 GB | ~12 tok/s | ✓ |
| Q6_K | 12.6 GB | ~15 tok/s | ✓ |
| Q5_K_M | 10.9 GB | ~18 tok/s | ✓ |
| Q4_K_M | 9.5 GB | ~21 tok/s | ✓ |
| Q3_K_M | 8.1 GB | ~25 tok/s | ✓ |
| Q2_K | 6.6 GB | ~33 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