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

AI model

Open weights: Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

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

231.8 GiB checkpoint tensor payload · 124.45 B stored tensor elements · BF16/F32

Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.

Capabilities

Open weights: Yes
Model license: other
Checkpoint tensor payload: 231.81 GiB

Input modalities

text
image

Output modalities

text

Processing & platform

Architecture: nemotron_h_omni

Connectivity & software

Connectivity & features

Language-backbone configuration position capacity: 262,144 tokens.
Publisher-listed full-model context capability: up to 1M tokens; the pinned language configuration lists 262,144 positions.