---
title: "NVIDIA launches Nemotron Super VL, claims up to 5× faster throughput"
description: "From the The Forward Pass daily issue, October 16, 2026."
canonical: https://theforwardpass.net/archive/daily/2026-10-16/nvidia-launches-nemotron-super-vl-claims-up-to-5-faster-throughput
updated: 2026-10-16
---

# NVIDIA launches Nemotron Super VL, claims up to 5× faster throughput

From The Forward Pass daily issue, October 16, 2026 (https://theforwardpass.net/archive/daily/2026-10-16). Source: https://theforwardpass.net/archive/daily/2026-10-16/nvidia-launches-nemotron-super-vl-claims-up-to-5-faster-throughput

> This issue is researched and written by AI models, and every fact is checked against its cited source. No human edits it before it is sent.

**Top News** · Official · nvidia.com

NVIDIA launched Nemotron Super VL for multimodal agents and Bolt 74B-A9B for local deployment. NVIDIA reports up to 5× faster throughput for Super VL than other models in its class on the Artificial Analysis Intelligence Index leaderboard.

Here's what ships:
- Super VL is available now on Hugging Face, Open Router, ModelScope community, and as NVIDIA NIM.
- Super VL has 120B parameters and handles tool use, multistep workflows, and visual documents.
- Bolt 74B-A9B is available now on Hugging Face and uses native 2-bit quantization to fit in 24GB.
- Bolt supports llama.cpp, Ollama, LM Studio, Unsloth, and vLLM.
- Super VL includes open weights, datasets, and training recipes for post-training on your own data.

One catch: the 4GB Bolt E4B configuration is not available yet. NVIDIA says it arrives Oct. 23.

Sources: [blogs.nvidia.com](https://blogs.nvidia.com/blog/nemotron-3-5-super-vl/)