Skip to main content
NV

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b-bf16

Full-precision BF16 release of NVIDIA Nemotron 3.5 Super VL for reasoning, coding, tool use and document/video understanding. It combines Mamba-2, MoE and attention with a C-RADIO vision encoder, has 120B total and 12B active parameters, and supports up to 1M tokens of context.

Compare
Context window
1M
Input
Image · Text · Video
Output
Text
Released
2026-10-15
Model parameters
120B
Active parameters
12B
Weights
Open
License
OpenMDW-1.1
Capabilities
Reasoning, Tool call

Pricing

No official pricing available.

Performance

Overall capability

25.0/100

Coding
—
Reasoning
—
Professional work
—
Knowledge & language
—

No evaluation results available.

Providers

No providers found

ModelRegistry · Catalog updated 2026-10-21