General model by z-lab · 35B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen3.6 35B A3B DFlash can run but will be tight at 82% of RAM. Consider a lower quantization or closing other apps.
~10 tok/s
Q3_K_M · 19.6 GB · Estimated
Alternative: Q2_K (15.7 GB, ~13 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 39.5 GB | ~5 tok/s | ✗ |
| Q6_K | 30.8 GB | ~6 tok/s | ✗ |
| Q5_K_M | 26.6 GB | ~7 tok/s | ✗ |
| Q4_K_M | 23.1 GB | ~8 tok/s | ✗ |
| Q3_K_M Recommended | 19.6 GB | ~10 tok/s | ✓ |
| Q2_K | 15.7 GB | ~13 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