Coding model by bullpoint · 14.44B parameters
Qwen3 Coder Next AWQ 4bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 69% of your RAM.
~162 tok/s
Q8_0 · 16.6 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 16.6 GB | ~162 tok/s | ✓ |
| Q6_K | 13.0 GB | ~213 tok/s | ✓ |
| Q5_K_M | 11.3 GB | ~251 tok/s | ✓ |
| Q4_K_M | 9.8 GB | ~294 tok/s | ✓ |
| Q3_K_M | 8.4 GB | ~355 tok/s | ✓ |
| Q2_K | 6.8 GB | ~461 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free