---
title: "NVIDIA releases Nemotron 3.5 Super VL, an open 120B multimodal model"
url: https://www.parallelquant.com/posts/nvidia-releases-nemotron-3-5-super-vl-an-open-120b-multimodal-model-137b1a
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/15/nvidia-nemotron-3-5-super-vl-release/
published: 2026-10-15T19:53:50.000Z
topics: ["llms", "open source"]
publisher: "Parallel Quant"
---

# NVIDIA releases Nemotron 3.5 Super VL, an open 120B multimodal model

*2026-10-15 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/15/nvidia-nemotron-3-5-super-vl-release/)*

NVIDIA released Nemotron 3.5 Super VL, an open mixture-of-experts model with 120B parameters, 12B active, and a 1M-token context. Its NVFP4 (4-bit) weights run on a single DGX Spark. Two smaller Bolt edge models were released alongside it.

**Why it matters:** Only 12B parameters are active per token, and the 4-bit weights fit on one small desktop box, so a capable multimodal agent model becomes feasible to self-host. It extends NVIDIA's push to supply open models that favor its own hardware formats.

**Topics:** llms, open source

---
Read the original: https://www.marktechpost.com/2026/10/15/nvidia-nemotron-3-5-super-vl-release/
Canonical: https://www.parallelquant.com/posts/nvidia-releases-nemotron-3-5-super-vl-an-open-120b-multimodal-model-137b1a
Published by Parallel Quant — https://www.parallelquant.com