Chat model by Mistral AI · 122.61B parameters · Released 2024-07-24
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Mistral Large Instruct 2407 requires 53.9 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 137.3 GB | ~1 tok/s | ✗ |
| Q6_K | 106.6 GB | ~2 tok/s | ✗ |
| Q5_K_M | 91.9 GB | ~2 tok/s | ✗ |
| Q4_K_M | 79.6 GB | ~2 tok/s | ✗ |
| Q3_K_M | 67.4 GB | ~3 tok/s | ✗ |
| Q2_K | 53.9 GB | ~4 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