nvidia/nemotron/nvidia-nemotron-3-ultra-550b-a55b-nvfp4
Source details
Source revision: abcfa162387e5fea3060af98d7675b438f84aa342c134f52ae47f79898af65c1
NVIDIA · Text
NVIDIA Nemotron models: Versions, specs, GPU requirements & hosting
NVIDIA Nemotron provides Ultra, Super, Nano, Omni and Lightning tiers optimized for different throughput and reasoning targets.
Overview and history
NVIDIA Nemotron is an official NVIDIA model family represented here through independently verified release, checkpoint, license, runtime and hardware evidence. NVIDIA Nemotron provides Ultra, Super, Nano, Omni and Lightning tiers optimized for different throughput and reasoning targets. Current public releases are grouped by the General, Omni, Speaker Diarization tracks so sibling sizes and specialist branches are not presented as false chronological generations.
FusionPointAI currently tracks 9 certified public NVIDIA Nemotron releases. The catalogue preserves release dates and evaluates Current, Recent, Previous and Legacy status within each model track rather than by database insertion order.
NVIDIA-optimized formats
Multiple scale tiers
Enterprise reasoning
Architecture and model range
The verified public range spans 0.1B to 550B total parameters and context windows up to 262,144 tokens. Each release states whether it is dense or mixture-of-experts and records active parameters separately when the official source publishes them.
Public releases9
Model tracks3
Current generationNVIDIA Nemotron 3.5 Lightning 30B-A3B
Last verified2026-09-04T00:00:00.000000Z
Generations, tracks and variants
General
Nemotron 3
Recent generation 3 sibling variantsNVIDIA Nemotron 3 Super 120B-A12B
120.0B parameters · 262,144 context
Super · MoE
NemotronHForCausalLM
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Base
Unknown / Not Recommendable
NVIDIA Nemotron 3 Ultra 550B-A55B
550.0B parameters · 262,144 context
Ultra · MoE
MoE Transformer
Unknown / Not Recommendable
nemotron-3-5
Current generation 4 sibling variantsNVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Base
Unknown / Not Recommendable
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
Unknown / Not Recommendable
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
Quantization
Unknown / Not Recommendable
NVIDIA Nemotron 3.5 Lightning 30B-A3B
30.0B parameters · 262,144 context
Fast · MoE
NemotronHForCausalLM
Unknown / Not Recommendable
Omni
Nemotron 3 Nano Omni
Current generationSpeaker diarization
Deployment ecosystem
Choose a specific NVIDIA Nemotron release and certified checkpoint before sizing hardware. FusionPointAI rejects unknown runtime configurations, calculates resident memory from total model weights, then distinguishes globally compatible GPUs from currently rentable inventory.
Validate the exact checkpoint license, runtime version, precision kernel, context length, concurrency and multi-GPU topology. Active MoE parameters affect compute, but resident model memory continues to use total stored weights.
Common use cases
High-throughput inference
Reasoning services
Multimodal agents
License overview
Licenses are certified per release, not inferred from the provider. Review the release page before commercial deployment because terms can differ between generations and variants.
Commercial-use status is a source-backed catalogue classification, not legal advice. Follow the linked official license and attribution requirements.
Release timeline
nvidia/nemotron/nvidia-nemotron-35-lightning-30b-a3b-nvfp4
Source details
Source revision: f3923f78a1a7f78f04eb3b3b86306923df43dfa7f72f5989ab0aa4c2eb8c54ff
nvidia/nemotron/nvidia-nemotron-35-lightning-30b-a3b-nvfp4-dspark
Source details
Source revision: b939d8a0adc9e4ab46fc50be6172409fca1a92a532e347d2274c153d5d538e26
nvidia/nemotron/nvidia-nemotron-35-lightning-30b-a3b-nvfp4-dflash
Source details
Source revision: 7659a063e177eb2dbeac048c499e30fd10c5a7ced958405c505318957fa23562
nvidia/nemotron/nemotron-3-ultra-550b-a55b
Source details
Source revision: ac6e67d70b7e8a6f10d1323aee594980c0fdb0a43eec104ffbe84e87897885ec
nvidia/nemotron/nemotron-3-5-lightning-30b-a3b
Source details
Source revision: dc17dd660dd197ae989def582e149d930b898c480ac56fbc28aef4ad5508fb32
nvidia/nemotron/nemotron-3-diarization-preview
Source details
Source revision: a43022e40b9883fb75078c47c5d4c995436863bb26e26f13a1a7e836ea519229
nvidia/nemotron/nemotron-3-super-120b-a12b
Source details
Source revision: 680e0e5a3131d196ec831e0f1d320c7e0a5405faac89108daf9591babe14134c
nvidia/nemotron/nemotron-3-nano-omni-30b-a3b-reasoning-fp8
Source details
Source revision: dd885e9548478d0d433c1239ed4598ad4a9faf7f58a8c706ab89885e5e2117fa
Frequently asked questions
Which NVIDIA Nemotron release is current?
Current releases are NVIDIA Nemotron 3.5 Lightning 30B-A3B, NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning FP8, evaluated within their respective tracks.
Can NVIDIA Nemotron be self-hosted?
Only releases with a verified official checkpoint and supported runtime configuration are presented as deployable.
Which GPU should run NVIDIA Nemotron?
GPU selection depends on the exact variant, checkpoint precision, context length and concurrency; use the release hardware recommendations rather than the family name alone.
Official references
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
- huggingface.co
Last verified: 2026-09-04