General model by nvidia · 56B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
Nemotron H 56B Base 8K requires 24.9 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 63.0 GB | ~3 tok/s | ✗ |
| Q6_K | 49.0 GB | ~4 tok/s | ✗ |
| Q5_K_M | 42.3 GB | ~4 tok/s | ✗ |
| Q4_K_M | 36.7 GB | ~5 tok/s | ✗ |
| Q3_K_M | 31.1 GB | ~6 tok/s | ✗ |
| Q2_K | 24.9 GB | ~8 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