General model by cyankiwi · 2B parameters
granite 4.0 h tiny AWQ 4bit fits comfortably in your 24 GB Mac using Q8_0 quantization, using 11% of your RAM.
~579 tok/s
Q8_0 · 2.7 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.7 GB | ~579 tok/s | ✓ |
| Q6_K | 2.2 GB | ~760 tok/s | ✓ |
| Q5_K_M | 2.0 GB | ~894 tok/s | ✓ |
| Q4_K_M | 1.8 GB | ~1,048 tok/s | ✓ |
| Q3_K_M | 1.6 GB | ~1,267 tok/s | ✓ |
| Q2_K | 1.4 GB | ~1,643 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free