Will this model run on your hardware?
Can I run NVIDIA: Nemotron 3 Ultra locally?
- 561B parameters (55B active, MoE)
- context up to 256K
- licence: other
- Weights: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · GGUF: unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 584.3 GB |
| UD-Q6_K | 460.7 GB |
| UD-Q5_K_M | 426.5 GB |
| UD-Q4_K_M | 359.2 GB |
| MXFP4 | 352.3 GB |
| UD-Q3_K_M | 274.0 GB |
Run it locally
ollama run hf.co/unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:UD-Q4_K_M
llama serve -hf unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:UD-Q4_K_M
LM Studio: open unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF