Chat model by BAAI · 5.44B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
AquilaChat2 7B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 27% of your RAM.
~30 tok/s
Q8_0 · 6.6 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 6.6 GB | ~30 tok/s | ✓ |
| Q6_K | 5.2 GB | ~39 tok/s | ✓ |
| Q5_K_M | 4.6 GB | ~46 tok/s | ✓ |
| Q4_K_M | 4.0 GB | ~54 tok/s | ✓ |
| Q3_K_M | 3.5 GB | ~65 tok/s | ✓ |
| Q2_K | 2.9 GB | ~84 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