General model by harley-ml · 0.01B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
LWTMoE 10M A6M fits comfortably in your 24 GB Mac using Q8_0 quantization, using 2% of your RAM.
— tok/s
Q8_0 · 0.5 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 0.5 GB | ~134,033 tok/s | ✓ |
| Q6_K | 0.5 GB | ~175,919 tok/s | ✓ |
| Q5_K_M | 0.5 GB | ~206,963 tok/s | ✓ |
| Q4_K_M | 0.5 GB | ~242,647 tok/s | ✓ |
| Q3_K_M | 0.5 GB | ~293,198 tok/s | ✓ |
| Q2_K | 0.5 GB | ~380,365 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