General model by ai4pd · 1.33B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
ProtGPT3 1.3B fits comfortably in your 24 GB Mac using Q8_0 quantization, using 8% of your RAM.
— tok/s
Q8_0 · 2.0 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 2.0 GB | ~421 tok/s | ✓ |
| Q6_K | 1.7 GB | ~553 tok/s | ✓ |
| Q5_K_M | 1.5 GB | ~650 tok/s | ✓ |
| Q4_K_M | 1.4 GB | ~762 tok/s | ✓ |
| Q3_K_M | 1.2 GB | ~921 tok/s | ✓ |
| Q2_K | 1.1 GB | ~1,195 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