Chat model by opengvlab · 7.94B parameters
InternVL3 8B Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 39% of your RAM.
~20 tok/s
Q8_0 · 9.4 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 9.4 GB | ~20 tok/s | ✓ |
| Q6_K | 7.4 GB | ~27 tok/s | ✓ |
| Q5_K_M | 6.4 GB | ~31 tok/s | ✓ |
| Q4_K_M | 5.6 GB | ~37 tok/s | ✓ |
| Q3_K_M | 4.8 GB | ~44 tok/s | ✓ |
| Q2_K | 4.0 GB | ~57 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free