edge LLM

Apple on-device foundation model (2025)

Apple's about 3B on-device model, accessed only through the Swift Foundation Models framework (guided generation, tool calling, LoRA adapters).

AppleUSA

Figure from the Apple on-device foundation model (2025) paper: Modeling overview for the Apple foundation models.

Levelmodel

Classedge LLM

Parametersnot in the notes

Contextnot in the notes

Released17 Jul 2025

Opennessproprietary

Runs onmobile or NPU, laptop, offline capable

Statusactive

R&D Topics

Quantization and edge inferenceproduced by Small language models (SLM)produced by

Identity

Developer: Apple
Family: not in the notes
Released: 17 Jul 2025 sourcesannouncement page
Weights published: –
Record checked: 10 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: not in the notes 2-bit quantization-aware training; KV-cache sharing
Total parameters: – sources
Active parameters: –
Checkpoint parameters: –
Note: About 3B
Context length: not in the notes
Input: text
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: proprietary
Licence: Proprietary sources
Access routes: internal only

Where this comes from

The licence file governs over registry tags and aggregator labels.

Deployment

Runs on: mobile or NPU, laptop, offline capable
Footprint: Footprint not stated; Apple silicon (iPhone, iPad, Mac)
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

Developer

Applebig tech, USA

Model

Apple on-device foundation model (2025)Apple, edge LLM

R&D TopicsQuantization and Edge Inference Small Language Models (SLM)

Use CasesIndustrial Copilots and Maintenance AssistantsIndustrial Indonesian and Regional-Language LLMsPublic Sector Telecom Domain LLMs and BenchmarksTelecomUse cases of models in the same R&D topic; none is recorded for this model itself.

Who Runs It

PT Pertamina Geothermal Energy Tbk (PGE)

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.

Graph

Organisations 1

Applebig tech, USADeveloper

R&D topics 2

Small Language Models (SLM)Models under about 10B parameters that fit consumer devices.produced by Quantization and Edge InferenceLower-bit weights and on-device serving.produced by

Sources

Apple Intelligence Foundation Language Models Tech Report 2025 machinelearning.apple.com https://machinelearning.apple.com/research/apple-foundation-models-tech-report-2025
Apple Intelligence Foundation Language Models: Tech Report 2025 arxiv.org https://arxiv.org/abs/2507.13575v2
arxiv.org/abs/2507.13575 https://arxiv.org/abs/2507.13575

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Apple On-Device Foundation Model (2025)", https://aurion.semai.id/models/apple-on-device-foundation-model-2025/, records of October 2026.