General model by nvidia · 13.51B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Nemotron Labs Diffusion 14B Base fits comfortably in your 24 GB Mac using Q8_0 quantization, using 65% of your RAM.
~12 tok/s
Q8_0 · 15.6 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 15.6 GB | ~12 tok/s | ✓ |
| Q6_K | 12.2 GB | ~16 tok/s | ✓ |
| Q5_K_M | 10.6 GB | ~18 tok/s | ✓ |
| Q4_K_M | 9.2 GB | ~22 tok/s | ✓ |
| Q3_K_M | 7.9 GB | ~26 tok/s | ✓ |
| Q2_K | 6.4 GB | ~34 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