General model by Microsoft · 20.91B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
OptiMind SFT fits comfortably in your 24 GB Mac using Q6_K quantization, using 77% of your RAM.
— tok/s
Q6_K · 18.6 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 23.8 GB | ~46 tok/s | ✗ |
| Q6_K Recommended | 18.6 GB | ~60 tok/s | ✓ |
| Q5_K_M | 16.1 GB | ~70 tok/s | ✓ |
| Q4_K_M | 14.0 GB | ~82 tok/s | ✓ |
| Q3_K_M | 11.9 GB | ~100 tok/s | ✓ |
| Q2_K | 9.6 GB | ~129 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free