Chat model by nvfp4 · 15.58B parameters
Qwen3 30B A3B Instruct 2507 FP4 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 75% of your RAM.
~94 tok/s
Q8_0 · 17.9 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 17.9 GB | ~94 tok/s | ✓ |
| Q6_K | 14.0 GB | ~124 tok/s | ✓ |
| Q5_K_M | 12.1 GB | ~146 tok/s | ✓ |
| Q4_K_M | 10.6 GB | ~171 tok/s | ✓ |
| Q3_K_M | 9.0 GB | ~206 tok/s | ✓ |
| Q2_K | 7.3 GB | ~268 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free