General model by dealignai · 12.59B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Nemotron 3 Super 120B A12B UNCENSORED JANG_2L fits comfortably in your 24 GB Mac using Q8_0 quantization, using 61% of your RAM.
— tok/s
Q8_0 · 14.5 GB · Benchmark needed
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 14.5 GB | ~141 tok/s | ✓ |
| Q6_K | 11.4 GB | ~185 tok/s | ✓ |
| Q5_K_M | 9.9 GB | ~217 tok/s | ✓ |
| Q4_K_M | 8.6 GB | ~255 tok/s | ✓ |
| Q3_K_M | 7.4 GB | ~308 tok/s | ✓ |
| Q2_K | 6.0 GB | ~399 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