Chat model by baichuan-inc · 5.55B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Baichuan2 7B Chat fits comfortably in your 24 GB Mac using Q8_0 quantization, using 28% of your RAM.
~29 tok/s
Q8_0 · 6.7 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 6.7 GB | ~29 tok/s | ✓ |
| Q6_K | 5.3 GB | ~38 tok/s | ✓ |
| Q5_K_M | 4.6 GB | ~45 tok/s | ✓ |
| Q4_K_M | 4.1 GB | ~52 tok/s | ✓ |
| Q3_K_M | 3.5 GB | ~63 tok/s | ✓ |
| Q2_K | 2.9 GB | ~82 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free