General model by llava-hf · 34.75B parameters
llava v1.6 34b hf can run but will be tight at 81% of RAM. Consider a lower quantization or closing other apps.
~10 tok/s
Q3_K_M · 19.5 GB
Alternative: Q2_K (15.6 GB, ~13 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 39.3 GB | ~5 tok/s | ✗ |
| Q6_K | 30.6 GB | ~6 tok/s | ✗ |
| Q5_K_M | 26.4 GB | ~7 tok/s | ✗ |
| Q4_K_M | 22.9 GB | ~8 tok/s | ✗ |
| Q3_K_M Recommended | 19.5 GB | ~10 tok/s | ✓ |
| Q2_K | 15.6 GB | ~13 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free