Model family timeline
Last updated Jun 4, 2026
Nemotron 3 model releases
A source-backed timeline for the Nemotron 3 model family, collecting release dates, labs, access details, context windows, and major lifecycle changes.
3
Models
1
Labs
3
Open
3
Recent
3 models
Nemotron 3 Ultra 550B-A55B
AvailableNVIDIAFrontierOpen weights
NVIDIA's largest Nemotron 3 open-weight hybrid Mamba-Transformer MoE, tuned for agentic reasoning, coding, planning, and tool calling.
Type
Hybrid
Params
550B
Context
1M
Top eval
—
Released
Jun 4, 2026
16d ago
Hybrid550B1M ctxJun 4, 2026
Nemotron 3 Super 120B-A12B
AvailableNVIDIAFrontierOpen weights
Open-weight hybrid Mamba-Transformer MoE designed for collaborative agents and high-volume enterprise workflows.
Type
Hybrid
Params
120B
Context
1M
Top eval
—
Released
Mar 16, 2026
3mo ago
Hybrid120B1M ctxMar 16, 2026
Nemotron 3 Nano 30B-A3B
AvailableNVIDIAOpen weights
Efficient Nemotron 3 MoE checkpoint for agentic reasoning and coding, activating about 3B parameters while supporting 1M-token contexts.
Type
Hybrid
Params
30B
Context
1M
Top eval
—
Released
Dec 15, 2025
6mo ago
Hybrid30B1M ctxDec 15, 2025