Chat model by Alibaba · 73.41B parameters
Qwen2.5 VL 72B Instruct requires 32.5 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 82.4 GB | ~2 tok/s | ✗ |
| Q6_K | 64.0 GB | ~3 tok/s | ✗ |
| Q5_K_M | 55.2 GB | ~3 tok/s | ✗ |
| Q4_K_M | 47.9 GB | ~4 tok/s | ✗ |
| Q3_K_M | 40.5 GB | ~5 tok/s | ✗ |
| Q2_K | 32.5 GB | ~6 tok/s | ✗ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free