multimodal LLMfamily
InternVL
Open multimodal models from OpenGVLab that pair a large InternViT vision encoder with open LLMs, from 1B to over 200B parameters, across versions 1 to 3.5.
Levelfamily
Classmultimodal LLM
Parametersnot in the notes
Contextnot in the notes
Released21 Dec 2023
Opennessunknown
Runs onnot in the notes
Statusactive
Lineage
InternVL3.5 241B A28B belongs to this familymultimodal LLM25 Aug 2025240.7BInternVL3.5 2B belongs to this familymultimodal LLM25 Aug 20252.35BInternVL3.5 8B belongs to this familymultimodal LLM25 Aug 20258.53BInternVL2 8B belongs to this familymultimodal LLM27 Jun 20248.08BWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
R&D Topics
Identity
- Developer
- Shanghai AI Lab
- Family
- not in the notes
- Released
- 21 Dec 2023 sourcesannouncement page
- 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
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- 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
- unknown
- Licence
- not in the notes 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: multilingual
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.
Industry Use Cases
No industry use case links this model.
Links
DeveloperShanghai AI Labnational lab, China
Shanghai AI Labnational lab, ChinaModelInternVLShanghai AI Lab, multimodal LLM
InternVLShanghai AI Lab, multimodal LLMR&D TopicsVisual Instruction Tuning
Use CasesRobot Inspection with Instrument ReadingIndustrialPathology Whole-Slide ImagingHealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Models 4
Organisations 1
Sources
- arxiv.org/abs/2312.14238 https://arxiv.org/abs/2312.14238
- github.com/OpenGVLab/InternVL https://github.com/OpenGVLab/InternVL
- modelscope.cn/models/OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-... https://www.modelscope.cn/models/OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-13B-448px
- huggingface.co/api/models?pipeline_tag=reinforcement-learnin... https://huggingface.co/api/models?pipeline_tag=reinforcement-learning&sort=downloads&limit=50
- huggingface.co/OpenGVLab/InternVL2-8B https://huggingface.co/OpenGVLab/InternVL2-8B
- huggingface.co/OpenGVLab/InternVL3_5-2B https://huggingface.co/OpenGVLab/InternVL3_5-2B
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "InternVL", https://aurion.semai.id/models/shanghai-ai-lab-internvl/, records of October 2026.