General model by norallm · 11.43B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
normistral 11b long fits comfortably in your 24 GB Mac using Q8_0 quantization, using 55% of your RAM.
~14 tok/s
Q8_0 · 13.3 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 13.3 GB | ~14 tok/s | ✓ |
| Q6_K | 10.4 GB | ~18 tok/s | ✓ |
| Q5_K_M | 9.0 GB | ~22 tok/s | ✓ |
| Q4_K_M | 7.9 GB | ~25 tok/s | ✓ |
| Q3_K_M | 6.7 GB | ~31 tok/s | ✓ |
| Q2_K | 5.5 GB | ~40 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