Chat model by redhatai · 4.07B parameters
Qwen2.5 VL 3B Instruct quantized.w8a8 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 21% of your RAM.
~40 tok/s
Q8_0 · 5.0 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 5.0 GB | ~40 tok/s | ✓ |
| Q6_K | 4.0 GB | ~52 tok/s | ✓ |
| Q5_K_M | 3.5 GB | ~61 tok/s | ✓ |
| Q4_K_M | 3.1 GB | ~72 tok/s | ✓ |
| Q3_K_M | 2.7 GB | ~86 tok/s | ✓ |
| Q2_K | 2.3 GB | ~112 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free