Chat model by opengvlab · 38.39B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
InternVL3_5 38B Instruct can run but will be tight at 72% of RAM. Consider a lower quantization or closing other apps.
~12 tok/s
Q2_K · 17.2 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 43.3 GB | ~4 tok/s | ✗ |
| Q6_K | 33.7 GB | ~5 tok/s | ✗ |
| Q5_K_M | 29.1 GB | ~6 tok/s | ✗ |
| Q4_K_M | 25.3 GB | ~8 tok/s | ✗ |
| Q3_K_M | 21.4 GB | ~9 tok/s | ✗ |
| Q2_K Recommended | 17.2 GB | ~12 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