General model by llava-hf · 0.89B parameters
llava onevision qwen2 0.5b ov hf fits comfortably in your 24 GB Mac using Q8_0 quantization, using 6% of your RAM.
~181 tok/s
Q8_0 · 1.5 GB
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.5 GB | ~181 tok/s | ✓ |
| Q6_K | 1.3 GB | ~237 tok/s | ✓ |
| Q5_K_M | 1.2 GB | ~279 tok/s | ✓ |
| Q4_K_M | 1.1 GB | ~327 tok/s | ✓ |
| Q3_K_M | 1.0 GB | ~395 tok/s | ✓ |
| Q2_K | 0.9 GB | ~513 tok/s | ✓ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free