General model by aubmindlab · 1.51B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
aragpt2 mega fits comfortably in your 24 GB Mac using Q8_0 quantization, using 9% of your RAM.
~106 tok/s
Q8_0 · 2.2 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.2 GB | ~106 tok/s | ✓ |
| Q6_K | 1.8 GB | ~140 tok/s | ✓ |
| Q5_K_M | 1.6 GB | ~164 tok/s | ✓ |
| Q4_K_M | 1.5 GB | ~193 tok/s | ✓ |
| Q3_K_M | 1.3 GB | ~233 tok/s | ✓ |
| Q2_K | 1.2 GB | ~302 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