General model by nbailab · 6.17B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
nb gpt j 6B torgersen alpaca fits comfortably in your 24 GB Mac using Q8_0 quantization, using 31% of your RAM.
~26 tok/s
Q8_0 · 7.4 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 7.4 GB | ~26 tok/s | ✓ |
| Q6_K | 5.8 GB | ~34 tok/s | ✓ |
| Q5_K_M | 5.1 GB | ~40 tok/s | ✓ |
| Q4_K_M | 4.5 GB | ~47 tok/s | ✓ |
| Q3_K_M | 3.9 GB | ~57 tok/s | ✓ |
| Q2_K | 3.2 GB | ~74 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