Multimodal model by opengvlab · 15.12B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
InternVL3_5 14B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 72% of your RAM.
~11 tok/s
Q8_0 · 17.4 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 17.4 GB | ~11 tok/s | ✓ |
| Q6_K | 13.6 GB | ~14 tok/s | ✓ |
| Q5_K_M | 11.8 GB | ~16 tok/s | ✓ |
| Q4_K_M | 10.3 GB | ~19 tok/s | ✓ |
| Q3_K_M | 8.7 GB | ~23 tok/s | ✓ |
| Q2_K | 7.1 GB | ~30 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free