Embedding model by BAAI · 0.33B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
bge large zh fits comfortably in your 24 GB Mac using Q8_0 quantization, using 4% of your RAM.
~487 tok/s
Q8_0 · 0.9 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 0.9 GB | ~487 tok/s | ✓ |
| Q6_K | 0.8 GB | ~640 tok/s | ✓ |
| Q5_K_M | 0.7 GB | ~752 tok/s | ✓ |
| Q4_K_M | 0.7 GB | ~882 tok/s | ✓ |
| Q3_K_M | 0.7 GB | ~1,066 tok/s | ✓ |
| Q2_K | 0.6 GB | ~1,383 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