Skip to content

NVLM

Open multimodal LLMs for vision and language tasks

Visit official site

What nvlm is

The project is the NVLM 1.0 family of multimodal large language models for vision and language tasks. Its weights and code are shared with the community.

What you can do with it

  • Run image caption generation
  • Try visual question answering
  • Compare text results after multimodal training

Getting started

  • Visit the project website
  • Download the released weights and code
  • Set up the environment and load the model

Pros & cons

✓ What we like

  • Weights and code are open to the community
  • The material compares it with GPT-4o and Llama 3-V 405B

! What to watch out for

  • Environment and dependencies must be configured
  • Weights and code are downloaded before use

FAQ

What is released?

Open source model weights and code.

Which tasks are named?

Image caption generation and visual question answering.

Last reviewed: 2026-11-15

More AI image generation tools

View all →

How we review