General model by torchllm · 0.29B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
HybridMoRMoE fits comfortably in your 24 GB Mac using Q8_0 quantization, using 3% of your RAM.
~555 tok/s
Q8_0 · 0.8 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 0.8 GB | ~555 tok/s | ✓ |
| Q6_K | 0.8 GB | ~728 tok/s | ✓ |
| Q5_K_M | 0.7 GB | ~856 tok/s | ✓ |
| Q4_K_M | 0.7 GB | ~1,004 tok/s | ✓ |
| Q3_K_M | 0.7 GB | ~1,213 tok/s | ✓ |
| Q2_K | 0.6 GB | ~1,574 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