General model by ludocomito · 5.1B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Minerva MoE 2x3B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 26% of your RAM.
— tok/s
Q8_0 · 6.2 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 6.2 GB | ~110 tok/s | ✓ |
| Q6_K | 4.9 GB | ~144 tok/s | ✓ |
| Q5_K_M | 4.3 GB | ~169 tok/s | ✓ |
| Q4_K_M | 3.8 GB | ~199 tok/s | ✓ |
| Q3_K_M | 3.3 GB | ~240 tok/s | ✓ |
| Q2_K | 2.7 GB | ~311 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