General model by ai-sweden-models · 20.92B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
gpt sw3 20b fits comfortably in your 24 GB Mac using Q6_K quantization, using 78% of your RAM.
~10 tok/s
Q6_K · 18.6 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 23.8 GB | ~8 tok/s | ✗ |
| Q6_K Recommended | 18.6 GB | ~10 tok/s | ✓ |
| Q5_K_M | 16.1 GB | ~12 tok/s | ✓ |
| Q4_K_M | 14.0 GB | ~14 tok/s | ✓ |
| Q3_K_M | 11.9 GB | ~17 tok/s | ✓ |
| Q2_K | 9.6 GB | ~22 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