General model by huihui-ai · 0.86B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Huihui MoE 0.8B 2E fits comfortably in your 24 GB Mac using Q8_0 quantization, using 6% of your RAM.
— tok/s
Q8_0 · 1.5 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 1.5 GB | ~356 tok/s | ✓ |
| Q6_K | 1.2 GB | ~467 tok/s | ✓ |
| Q5_K_M | 1.1 GB | ~550 tok/s | ✓ |
| Q4_K_M | 1.1 GB | ~645 tok/s | ✓ |
| Q3_K_M | 1.0 GB | ~779 tok/s | ✓ |
| Q2_K | 0.9 GB | ~1,010 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