Chat model by Alibaba · 2.44B parameters
Qwen3 VL 2B Instruct FP8 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 13% of your RAM.
~66 tok/s
Q8_0 · 3.2 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 3.2 GB | ~66 tok/s | ✓ |
| Q6_K | 2.6 GB | ~87 tok/s | ✓ |
| Q5_K_M | 2.3 GB | ~102 tok/s | ✓ |
| Q4_K_M | 2.1 GB | ~119 tok/s | ✓ |
| Q3_K_M | 1.8 GB | ~144 tok/s | ✓ |
| Q2_K | 1.6 GB | ~187 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free