GeekRadar / The comparison desk

COMPARE.

AI models

nvidia

Nemotron Cascade 2 30B A3B

AI model Released Mar 19, 2026

Context window: 256,000 tokens
Maximum output: 32,768 tokens
Open weights: Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Nemotron Cascade 2 30B A3B

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Context window: 256,000 tokens
Maximum output: 32,768 tokens
Reasoning: Yes
Tool calling: Yes
Open weights: Yes
Model license: other

Input modalities

text

Output modalities

text

Processing & platform

Architecture: nemotron_h