General model by yunconglong · 12.88B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
MoE_13B_DPO fits comfortably in your 24 GB Mac using Q8_0 quantization, using 62% of your RAM.
— tok/s
Q8_0 · 14.9 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 14.9 GB | ~12 tok/s | ✓ |
| Q6_K | 11.6 GB | ~16 tok/s | ✓ |
| Q5_K_M | 10.1 GB | ~19 tok/s | ✓ |
| Q4_K_M | 8.8 GB | ~23 tok/s | ✓ |
| Q3_K_M | 7.5 GB | ~27 tok/s | ✓ |
| Q2_K | 6.1 GB | ~35 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