Chat model by Alibaba · 8.29B parameters · Released 2025-01-26
Qwen2.5 VL 7B Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 41% of your RAM.
~19 tok/s
Q8_0 · 9.7 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 9.7 GB | ~19 tok/s | ✓ |
| Q6_K | 7.7 GB | ~25 tok/s | ✓ |
| Q5_K_M | 6.7 GB | ~30 tok/s | ✓ |
| Q4_K_M | 5.9 GB | ~35 tok/s | ✓ |
| Q3_K_M | 5.0 GB | ~42 tok/s | ✓ |
| Q2_K | 4.1 GB | ~55 tok/s | ✓ |
GGUF Sources
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free