General model by nvidia · 67.23B parameters
NVIDIA Nemotron 3 Super 120B A12B NVFP4 requires 29.8 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 75.5 GB | ~2 tok/s | ✗ |
| Q6_K | 58.7 GB | ~3 tok/s | ✗ |
| Q5_K_M | 50.6 GB | ~4 tok/s | ✗ |
| Q4_K_M | 43.9 GB | ~4 tok/s | ✗ |
| Q3_K_M | 37.2 GB | ~5 tok/s | ✗ |
| Q2_K | 29.8 GB | ~7 tok/s | ✗ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free