General model by cyankiwi · 1.76B parameters
Qwen3 VL 4B Thinking AWQ 4bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 10% of your RAM.
~91 tok/s
Q8_0 · 2.5 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.5 GB | ~91 tok/s | ✓ |
| Q6_K | 2.0 GB | ~120 tok/s | ✓ |
| Q5_K_M | 1.8 GB | ~141 tok/s | ✓ |
| Q4_K_M | 1.6 GB | ~165 tok/s | ✓ |
| Q3_K_M | 1.5 GB | ~200 tok/s | ✓ |
| Q2_K | 1.3 GB | ~259 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free