Chat model by opengvlab · 40.07B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
InternVL Chat V1 2 can run but will be tight at 75% of RAM. Consider a lower quantization or closing other apps.
~11 tok/s
Q2_K · 18.0 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 45.2 GB | ~4 tok/s | ✗ |
| Q6_K | 35.2 GB | ~5 tok/s | ✗ |
| Q5_K_M | 30.4 GB | ~6 tok/s | ✗ |
| Q4_K_M | 26.4 GB | ~7 tok/s | ✗ |
| Q3_K_M | 22.4 GB | ~9 tok/s | ✗ |
| Q2_K Recommended | 18.0 GB | ~11 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