General model by gordonhu · 7.05B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
MQT LLaVA 7b fits comfortably in your 24 GB Mac using Q8_0 quantization, using 35% of your RAM.
~23 tok/s
Q8_0 · 8.4 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 8.4 GB | ~23 tok/s | ✓ |
| Q6_K | 6.6 GB | ~30 tok/s | ✓ |
| Q5_K_M | 5.8 GB | ~35 tok/s | ✓ |
| Q4_K_M | 5.1 GB | ~41 tok/s | ✓ |
| Q3_K_M | 4.3 GB | ~50 tok/s | ✓ |
| Q2_K | 3.6 GB | ~65 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