Chat model by stelterlab · 4.61B parameters
Qwen3 30B A3B Instruct 2507 AWQ fits comfortably in your 24 GB Mac using Q8_0 quantization, using 24% of your RAM.
~319 tok/s
Q8_0 · 5.6 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 5.6 GB | ~319 tok/s | ✓ |
| Q6_K | 4.5 GB | ~419 tok/s | ✓ |
| Q5_K_M | 3.9 GB | ~493 tok/s | ✓ |
| Q4_K_M | 3.5 GB | ~578 tok/s | ✓ |
| Q3_K_M | 3.0 GB | ~698 tok/s | ✓ |
| Q2_K | 2.5 GB | ~906 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free