multimodal LLMfamily
FastVLM
Vision language models with a hybrid vision encoder that emits fewer tokens for high-resolution images, cutting time to first token on devices.
Levelfamily
Classmultimodal LLM
Parametersnot in the notes
Contextnot in the notes
Released17 Dec 2024
Opennessopen weights restricted
Runs onmobile or NPU, laptop
Statusactive
Lineage
FastVLM 0.5B belongs to this familymultimodal LLM25 Aug 2025758.83MFastVLM 7B belongs to this familymultimodal LLM25 Aug 20257.76BWhere 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.
Identity
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
- hybrid FastViTHD hybrid convolution-transformer vision encoder with an LLM
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text, image
- 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 restricted
- Licence
- Apple Machine Learning Research Model License (apple-amlr) sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- mobile or NPU, laptop
- 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.
Industry Use Cases
No industry use case links this model.
Links
DeveloperApplebig tech, USA
Applebig tech, USAModelFastVLMApple, multimodal LLM
FastVLMApple, multimodal LLMUse CasesIndustrial Copilots and Maintenance AssistantsIndustrialIndonesian and Regional-Language LLMsPublic SectorTelecom Domain LLMs and BenchmarksTelecomRobot Inspection with Instrument ReadingIndustrial+1 moreUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026
Siemens Erlangen electronics factoryPlanned, 6 Jan 2026
ADNOC OffshoreIn production, 9 Sep 2025
Aker BPIn production, 9 Sep 2025+10 moreDeployments of these use cases; none names this model.
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026Siemens Erlangen electronics factoryPlanned, 6 Jan 2026ADNOC OffshoreIn production, 9 Sep 2025Aker BPIn production, 9 Sep 2025+10 moreDeployments of these use cases; none names this model.Organisations 1
Sources
- arxiv.org/abs/2412.13303 https://arxiv.org/abs/2412.13303
- github.com/apple/ml-fastvlm https://github.com/apple/ml-fastvlm
- huggingface.co/apple/FastVLM-0.5B https://huggingface.co/apple/FastVLM-0.5B
- huggingface.co/apple/FastVLM-7B https://huggingface.co/apple/FastVLM-7B
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "FastVLM", https://aurion.semai.id/models/apple-fastvlm/, records of October 2026.