AI models
LongVILA-7B
Parameters
7B
Published
Aug 19, 2024
LongVILA-7B is an AI model developed by NVIDIA, Massachusetts Institute of Technology (MIT), University of California (UC) Berkeley and UT Austin (United States), first published in August 2024. It works in the multimodal, video and language domain, on tasks such as video, video description, visual question answering and language modeling/generation.
Epoch AI has no training-compute estimate for this model. The model has 7,000,000,000 parameters.
Access: Open weights (non-commercial). Its weights are openly available. It is built on top of Qwen2-7B. The reference paper has 264 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- NVIDIA, Massachusetts Institute of Technology (MIT), University of California (UC) Berkeley, UT Austin
- Country of organization
- United States
- Domain
- Multimodal, Video, Language
- Task
- Video, Video description, Visual question answering, Language modeling/generation
- Parameters
- 7,000,000,000
- Chips used
- 256
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Base model
- Qwen2-7B
- Citations
- 264
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models