Chat model by lmms-lab · 4.74B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
LLaVA OneVision 1.5 4B Instruct fits comfortably in your 24 GB Mac using Q8_0 quantization, using 24% of your RAM.
~34 tok/s
Q8_0 · 5.8 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 5.8 GB | ~34 tok/s | ✓ |
| Q6_K | 4.6 GB | ~45 tok/s | ✓ |
| Q5_K_M | 4.0 GB | ~52 tok/s | ✓ |
| Q4_K_M | 3.6 GB | ~61 tok/s | ✓ |
| Q3_K_M | 3.1 GB | ~74 tok/s | ✓ |
| Q2_K | 2.6 GB | ~96 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free