multimodal LLM
LongVU
Video language model that adaptively compresses frames in space and time so it can understand long videos within a limited context.
Levelmodel
Classmultimodal LLM
Parameters7.67B
Contextnot in the notes
Released18 Oct 2024
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Identity
- Developer
- Meta, King Abdullah University of Science and Technology
- Family
- not in the notes
- Released
- 18 Oct 2024 sourcesregistry date
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- 7.67B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- Parameter count from the safetensors index on Hugging Face.
- Context length
- not in the notes
- Input
- text, image, video
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelLongVUMeta, multimodal LLM
LongVUMeta, multimodal LLMR&D TopicsVideo Understanding with Language Models
Use CasesClinical LLM (Frontier Proprietary)HealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026FlatironIn production, 11 Jan 2026Novo NordiskIn production, 11 Jan 2026+13 moreDeployments of these use cases; none names this model.
Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026FlatironIn production, 11 Jan 2026Novo NordiskIn production, 11 Jan 2026+13 moreDeployments of these use cases; none names this model.Organisations 2
Sources
- huggingface.co/Vision-CAIR/LongVU_Qwen2_7B https://huggingface.co/Vision-CAIR/LongVU_Qwen2_7B
- huggingface.co/api/models?pipeline_tag=video-text-to-text&so... https://huggingface.co/api/models?pipeline_tag=video-text-to-text&sort=likes&limit=50
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "LongVU", https://aurion.semai.id/models/meta-longvu/, records of October 2026.