DAMO-NLP-SG/VideoLLaMA3

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1179 stars · 89 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

VideoLLaMA 3 is a frontier multimodal foundation model for image and video understanding, released with checkpoints, inference code, and demos. It is a research model from DAMO NLP-SG built on vision-language modeling for video and image QA.

Use cases

• understand and answer questions about videos
• video question answering with an LLM
• image understanding with a multimodal model
• analyze long videos frame by frame
• build a video chatbot
• run a vision-language model on GPU

When to choose

• you need open-weights video/image understanding with an LLM
• you want a research-grade multimodal model with demos and checkpoints
• you need Apache-2.0 licensed video LLM code

When to avoid

• you need lightweight CPU-only inference
• you need production video analytics pipelines rather than a research model
• you need audio understanding (see VideoLLaMA 2)

Facets

library · maturity active

machine-learning deep-learning llm-inference computer-vision video-processing image-processing nlp artificial-intelligence large-language-models computer-vision image-processing deep-learning python cross-platform multimodal video-llm vision-language-model video-understanding foundation-model huggingface research video natural-language-processing gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="DAMO-NLP-SG/VideoLLaMA3")