Coding model by bigatuna · 9.41B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Qwen3.5 9b Sushi Coder RL fits comfortably in your 24 GB Mac using Q8_0 quantization, using 46% of your RAM.
~17 tok/s
Q8_0 · 11.0 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 11.0 GB | ~17 tok/s | ✓ |
| Q6_K | 8.6 GB | ~22 tok/s | ✓ |
| Q5_K_M | 7.5 GB | ~26 tok/s | ✓ |
| Q4_K_M | 6.6 GB | ~31 tok/s | ✓ |
| Q3_K_M | 5.6 GB | ~37 tok/s | ✓ |
| Q2_K | 4.6 GB | ~48 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