General model by nvidia · 253.4B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Llama 3_1 Nemotron Ultra 253B CPT v1 requires 110.9 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 283.2 GB | ~1 tok/s | ✗ |
| Q6_K | 219.8 GB | ~1 tok/s | ✗ |
| Q5_K_M | 189.4 GB | ~1 tok/s | ✗ |
| Q4_K_M | 164.1 GB | ~1 tok/s | ✗ |
| Q3_K_M | 138.7 GB | ~1 tok/s | ✗ |
| Q2_K | 110.9 GB | ~2 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