NVIDIA Nemotron 3 Ultra 550B A55B NVFP4

Name: NVIDIA Nemotron 3 Ultra 550B A55B NVFP4
Author: NVIDIA

by NVIDIA

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released December 2025262K context≈ 196,608 words550B params

A massive mixture-of-experts model from NVIDIA with 550 billion total parameters but only 55 billion active at a time, making it more computationally tractable than its size suggests. It runs in NVIDIA's custom NVFP4 precision format, meaning it's tightly coupled to NVIDIA hardware and tooling — don't expect to run this casually on commodity setups. Geared toward text tasks at scale, it brings a large context window of 262K tokens, useful for long-document work.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Coding

Moderate

Instruction Following

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4

by NVIDIA

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released December 2025262K context≈ 196,608 words550B params

A massive mixture-of-experts model from NVIDIA with 550 billion total parameters but only 55 billion active at a time, making it more computationally tractable than its size suggests. It runs in NVIDIA's custom NVFP4 precision format, meaning it's tightly coupled to NVIDIA hardware and tooling — don't expect to run this casually on commodity setups. Geared toward text tasks at scale, it brings a large context window of 262K tokens, useful for long-document work.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Coding

Moderate

Instruction Following

Glossary

Context WindowThe maximum number of tokens a model can process in a single conversation or prompt.NVFP4 PrecisionA low-precision numerical format that uses 4 bits per weight, developed by NVIDIA to compress models for efficient inference on consumer hardware.NVFP4 PrecisionA low-precision numerical format optimized by NVIDIA that uses fewer bits per number than standard formats, enabling efficient inference on NVIDIA GPUs while maintaining reasonable accuracy.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.PrecisionThe level of numerical detail a model uses to represent its internal values; higher precision means more accurate calculations but requires more memory.TokensThe basic units of text that a language model processes, typically representing words or word fragments.

Capabilities

Capabilities

Use Case Fit

Glossary