General model by llava-hf · 13.35B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
llava v1.6 vicuna 13b hf fits comfortably in your 24 GB Mac using Q8_0 quantization, using 64% of your RAM.
~12 tok/s
Q8_0 · 15.4 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 15.4 GB | ~12 tok/s | ✓ |
| Q6_K | 12.1 GB | ~16 tok/s | ✓ |
| Q5_K_M | 10.5 GB | ~19 tok/s | ✓ |
| Q4_K_M | 9.1 GB | ~22 tok/s | ✓ |
| Q3_K_M | 7.8 GB | ~26 tok/s | ✓ |
| Q2_K | 6.3 GB | ~34 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free