Chat model by cyankiwi · 5.85B parameters
Qwen3 VL 30B A3B Instruct AWQ 4bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 29% of your RAM.
~345 tok/s
Q8_0 · 7.0 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 7.0 GB | ~345 tok/s | ✓ |
| Q6_K | 5.6 GB | ~453 tok/s | ✓ |
| Q5_K_M | 4.9 GB | ~533 tok/s | ✓ |
| Q4_K_M | 4.3 GB | ~625 tok/s | ✓ |
| Q3_K_M | 3.7 GB | ~755 tok/s | ✓ |
| Q2_K | 3.0 GB | ~980 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free