multimodal LLM

InternVideo2.5 Chat 8B

Video multimodal model built on InternVL2.5 with long and rich context modelling, for fine-grained understanding of long videos.

Shanghai AI LabChina

Levelmodel

Classmultimodal LLM

Parameters8.4B

Contextnot in the notes

Released22 Jan 2025

Opennessopen weights permissive

Runs onnot in the notes

Statusactive

R&D Topics

Video understanding with language modelsproduced by Visual instruction tuningproduced by

Identity

Developer: Shanghai AI Lab
Family: not in the notes
Released: 22 Jan 2025 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: 8.4B 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: Model card languages: en

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

Developer

Shanghai AI Labnational lab, China

Model

InternVideo2.5 Chat 8BShanghai AI Lab, multimodal LLM

R&D TopicsVideo Understanding with Language Models Visual Instruction Tuning

Use CasesClinical LLM (Frontier Proprietary)Healthcare Robot Inspection with Instrument ReadingIndustrial Pathology Whole-Slide ImagingHealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.

Who Runs It

Banner HealthIn production, 11 Jan 2026 CommureIn production, 11 Jan 2026 FlatironIn production, 11 Jan 2026 Novo NordiskIn production, 11 Jan 2026+13 moreDeployments of these use cases; none names this model.

Graph

Organisations 1

Shanghai AI Labnational lab, ChinaDeveloper

R&D topics 2

Visual Instruction TuningConnecting a vision encoder to a language model and training it on image-grounded instruc…produced byVideo Understanding with Language ModelsVision-language models that summarise, search and answer questions about long videos.produced by

Sources

huggingface.co/OpenGVLab/InternVideo2_5_Chat_8B https://huggingface.co/OpenGVLab/InternVideo2_5_Chat_8B
huggingface.co/api/models?pipeline_tag=video-text-to-text&so... https://huggingface.co/api/models?pipeline_tag=video-text-to-text&sort=downloads&limit=50

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "InternVideo2.5 Chat 8B", https://aurion.semai.id/models/shanghai-ai-lab-internvideo2-5-chat-8b/, records of October 2026.