Coding model by btbtyler09 · 9.3B parameters
Qwen3 Coder 30B A3B Instruct gptq 8bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 45% of your RAM.
~158 tok/s
Q8_0 · 10.9 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 10.9 GB | ~158 tok/s | ✓ |
| Q6_K | 8.5 GB | ~208 tok/s | ✓ |
| Q5_K_M | 7.4 GB | ~244 tok/s | ✓ |
| Q4_K_M | 6.5 GB | ~286 tok/s | ✓ |
| Q3_K_M | 5.6 GB | ~346 tok/s | ✓ |
| Q2_K | 4.6 GB | ~449 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free