NVIDIA

NVIDIA Nemotron 3.5 Super VL 120B A12B

Name: NVIDIA Nemotron 3.5 Super VL 120B A12B
Author: NVIDIA

NVIDIA Nemotron 3.5 Super VL 120B A12B is a NVIDIA model with 1.05M context, Not verified in / Not verified out per million tokens, last verified November 3, 2026. Open weights: yes. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

NVIDIA's open multimodal MoE for specialized enterprise agents that reason over text and vision together.

Recorded profile verification November 3, 2026Individual provider fields may change

AI model specification details
Specification	NVIDIA Nemotron 3.5 Super VL 120B A12B
Provider	NVIDIA
Tier	Frontier
Context window	1.05M
Max output	Not verifiedUnverified
Input / 1M tokens	Not verifiedUnverified
Output / 1M tokens	Not verifiedUnverified
Weights	Open
Parameters	120B total / 12B active (sparse MoE)
Reasoning levels	Not verifiedUnverified
Modalities	text, image
License	OpenMDW License Agreement 1.1
Released	October 15, 2026

Pricing tiers: Downloadable weights for self-hosting and post-training; no first-party per-token API tariff is published. Hosted route prices, where offered by providers, are separate.

Best for

Multimodal enterprise agents
Document and visual workflows
Post-trained specialized agents

Watch out

Exact output cap is unverified from retained sources. The 1,048,576 figure is the checkpoint position limit. Publisher throughput and customer outcome claims are not independent public-board observations.

History

NVIDIA Nemotron 3.5 Super VL 120B A12B timeline

Release and status events for this model that passed two-source verification — dated, sourced, and linked.

NVIDIA Nemotron 3.5 Super VL 120B A12BReleaseOctober 15, 2026
NVIDIA published the open Nemotron 3.5 Super VL multimodal MoE for specialized enterprise agents, with downloadable weights.
NVIDIA Nemotron 3.5 Super VL article, published October 15

Source receipts

Catalog figures for this model were checked against the following sources.

NVIDIA Nemotron 3.5 Super VL article: October 15 publication, scale and positioning (accessed 2026-11-03)
NVIDIA Nemotron 3.5 Super VL checkpoint record: identity and pipeline (accessed 2026-11-03)
Nemotron 3.5 Super VL checkpoint config: architecture and position limit (accessed 2026-11-03)

Common questions

NVIDIA Nemotron 3.5 Super VL 120B A12B

Answered from the verified figures on this page rather than general guidance.

What is NVIDIA Nemotron 3.5 Super VL 120B A12B's context window?

NVIDIA Nemotron 3.5 Super VL 120B A12B accepts about 1.05M tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.

What is NVIDIA Nemotron 3.5 Super VL 120B A12B best for?

NVIDIA Nemotron 3.5 Super VL 120B A12B is a frontier tier from NVIDIA. It suits multimodal enterprise agents, document and visual workflows, post-trained specialized agents. Exact output cap is unverified from retained sources. The 1,048,576 figure is the checkpoint position limit. Publisher throughput and customer outcome claims are not independent public-board observations.

Can I self-host NVIDIA Nemotron 3.5 Super VL 120B A12B?

NVIDIA Nemotron 3.5 Super VL 120B A12B publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.

Model comparison catalog Benchmark library