Nvidia has released an open-source large language model (LLM) called NVLM 1.0 that performs on par with leading proprietary models from OpenAI, Anthropic, Meta, and Google.
The NVLM 1.0 family includes the 72 billion-parameter NVLM-D-72B model and achieves state-of-the-art results on vision-language tasks.
The model demonstrates improved text-only responses and enhanced math and coding capabilities.
Nvidia plans to make the model's source code available, positioning it as a foundation for third-party developers to build their own chatbots and AI applications.