Chat model by Meta · 10.67B parameters · Released 2024-09-18
Llama 3.2 11B Vision Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 52% of your RAM.
~15 tok/s
Q8_0 · 12.4 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 12.4 GB | ~15 tok/s | ✓ |
| Q6_K | 9.7 GB | ~20 tok/s | ✓ |
| Q5_K_M | 8.5 GB | ~23 tok/s | ✓ |
| Q4_K_M | 7.4 GB | ~27 tok/s | ✓ |
| Q3_K_M | 6.3 GB | ~33 tok/s | ✓ |
| Q2_K | 5.1 GB | ~43 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free