Chat model by cyankiwi · 5.31B parameters
Qwen3 30B A3B Instruct 2507 AWQ 4bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 27% of your RAM.
~277 tok/s
Q8_0 · 6.4 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 6.4 GB | ~277 tok/s | ✓ |
| Q6_K | 5.1 GB | ~364 tok/s | ✓ |
| Q5_K_M | 4.5 GB | ~428 tok/s | ✓ |
| Q4_K_M | 3.9 GB | ~502 tok/s | ✓ |
| Q3_K_M | 3.4 GB | ~606 tok/s | ✓ |
| Q2_K | 2.8 GB | ~786 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free