Chat model by cyankiwi · 2.91B parameters
Qwen3 VL 8B Instruct AWQ 4bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 16% of your RAM.
~55 tok/s
Q8_0 · 3.7 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 3.7 GB | ~55 tok/s | ✓ |
| Q6_K | 3.0 GB | ~73 tok/s | ✓ |
| Q5_K_M | 2.7 GB | ~85 tok/s | ✓ |
| Q4_K_M | 2.4 GB | ~100 tok/s | ✓ |
| Q3_K_M | 2.1 GB | ~121 tok/s | ✓ |
| Q2_K | 1.8 GB | ~157 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free