Checked fact 170717 Oct 2026Models and releases

Nvidia's developer blog, dated 15 October 2026, describes Nemotron 3.5 Super VL as a 120B-parameter mixture-of-experts architecture that activates 12B parameters per token.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

Its 120B-parameter mixture-of-experts (MoE) architecture activates 12B parameters per token

What the source said when we opened it, on 17 Oct 2026.

The source

NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning
NVIDIA Technical Blog · 2026-10-15

Open the source archived copy

Checked

Checked by the notis newsroom on 17 Oct 2026, against the source above.

In the story

Nvidia released Nemotron 3.5 Super VL, a 120B open model taking images and video, with a 1M-token context. 17 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Nvidia's developer blog, dated 15 October 2026, describes Nemotron 3.5 Super VL as a 120B-parameter mixture-of-experts architecture that activates 12B parameters per token.” ai notis, checked 17 Oct 2026. Source: NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning (NVIDIA Technical Blog). https://ainotis.com/c/1707

As a reference (APA style)

ai notis. (2026, October 17). Nvidia's developer blog, dated 15 October 2026, describes Nemotron 3.5 Super VL as a 120B-parameter mixture-of-experts architecture that activates 12B parameters per token [Checked claim 1707]. ai notis. https://ainotis.com/c/1707

Anyone may quote this address. It does not change; if we correct the story, this page says so.