Chat model by Alibaba · 14.77B parameters
Qwen2.5 14B Instruct AWQ fits comfortably in your 24 GB Mac using Q8_0 quantization, using 71% of your RAM.
~11 tok/s
Q8_0 · 17.0 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 17.0 GB | ~11 tok/s | ✓ |
| Q6_K | 13.3 GB | ~14 tok/s | ✓ |
| Q5_K_M | 11.5 GB | ~17 tok/s | ✓ |
| Q4_K_M | 10.0 GB | ~20 tok/s | ✓ |
| Q3_K_M | 8.6 GB | ~24 tok/s | ✓ |
| Q2_K | 6.9 GB | ~31 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free