Lab release history
Last updated Jun 4, 2026
NVIDIA model releases
GPU platform company increasingly shipping open Nemotron foundation models. This page collects the lab's model releases, lifecycle events, source links, and model metadata in one crawlable record.
6 models
Nemotron 3 Ultra 550B-A55B
AvailableNVIDIA's largest Nemotron 3 open-weight hybrid Mamba-Transformer MoE, tuned for agentic reasoning, coding, planning, and tool calling.
Nemotron 3 Super 120B-A12B
AvailableOpen-weight hybrid Mamba-Transformer MoE designed for collaborative agents and high-volume enterprise workflows.
Nemotron 3 Nano 30B-A3B
AvailableEfficient Nemotron 3 MoE checkpoint for agentic reasoning and coding, activating about 3B parameters while supporting 1M-token contexts.
Llama-3.3-Nemotron-Super-49B
AvailableOpen Llama Nemotron reasoning model from NVIDIA's 2025 Nemotron family.
Llama-3.1-Nemotron-70B
AvailableNVIDIA-tuned Llama 3.1 70B instruction model optimized with Nemotron reward and alignment recipes.
Nemotron-4 340B
AvailableNVIDIA's large open model family for synthetic data generation and reward modeling.