Chat model by BAAI · 8.49B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Emu3 Chat fits comfortably in your 24 GB Mac using Q8_0 quantization, using 42% of your RAM.
~19 tok/s
Q8_0 · 10.0 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 10.0 GB | ~19 tok/s | ✓ |
| Q6_K | 7.8 GB | ~25 tok/s | ✓ |
| Q5_K_M | 6.8 GB | ~29 tok/s | ✓ |
| Q4_K_M | 6.0 GB | ~34 tok/s | ✓ |
| Q3_K_M | 5.1 GB | ~41 tok/s | ✓ |
| Q2_K | 4.2 GB | ~54 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