Apple Intelligence local AI explained: on-device models, Private Cloud Compute, and external services

Research snapshot: July 22, 2026 · editorial review: August 15, 2026. The stable baseline is iOS 26, iPadOS 26, and macOS Tahoe 26. At WWDC 2026, Apple announced the next generation for iOS 27, iPadOS 27, and macOS 27. Parts of that generation are in developer or public beta and are planned for general availability in fall 2026. Apple also says that the more personal Siri capabilities remain under development. ¹²

Apple Intelligence is frequently described as “Apple’s local LLM,” but that label hides most of the architecture. It is not one model and it is not simply a renamed Siri. Apple combines several on-device language, vision, audio, and classification models with operating-system services, app tools, Private Cloud Compute (PCC), and optional third-party integrations such as ChatGPT. ³⁴⁵

How to read these claims

• Officially confirmed: documented by Apple, a platform vendor, or the relevant open-source project.
• Preview/Beta: announced by Apple but not yet final or universally deployed on July 22, 2026.
• Architecture-level conclusion: a reasonable inference, not a disclosed internal Apple implementation detail.
• Not published: Apple has not provided the necessary data.

Key takeaways

• Apple Intelligence is a hybrid AI architecture. Some requests stay on the device, more demanding work can move to PCC, and selected experiences can invoke an external provider. ³⁴⁵
• Apple’s 2025 technical report described a highly compressed on-device language model with roughly 3 billion parameters. In June 2026, Apple introduced AFM 3 Core and the sparse multimodal AFM 3 Core Advanced, which has 20 billion total parameters but activates only 1–4 billion for a request. ⁶⁷
• AFM 3 Core Advanced keeps the full expert set in NAND flash and loads a selected subset into active memory. Apple limits this path to its most capable silicon configurations. ⁶
• Apple does not publish the complete automatic routing policy between the device, PCC, and external models. A feature name alone therefore cannot prove where every request was processed. ⁴⁸
• Apple currently lists 7 GB of device storage as an Apple Intelligence requirement on supported iPhone, iPad, and Mac models. It does not publish a full model-by-model disk or RAM breakdown. ¹
• The Foundation Models framework exposes Apple’s system model through native Swift APIs. The 2026 generation expands the framework with multimodal input, model-provider protocols, PCC access for eligible developers, evaluation tools, Dynamic Profiles, a command-line tool, and a Python SDK. ⁹¹⁰¹¹
• MLX, Core ML, Core AI, and llama.cpp can all run local AI workloads on Apple hardware, but they are not interchangeable with Apple Intelligence itself. ^12131415

What is Apple Intelligence?

Apple calls Apple Intelligence a personal intelligence system built into its operating systems. In practice, it is a coordinated platform rather than a single general-purpose chatbot. The platform connects generative models to app actions and relevant personal context while applying data-minimization, permission, safety, and routing rules. ³¹⁶

A useful architectural breakdown is:

1. User-facing experiences: Writing Tools, message and notification summaries, Siri, Genmoji, Image Playground, visual intelligence, smart actions in Shortcuts, translation, and app-specific features.
2. System orchestration: operating-system services assemble the required context, expose approved tools, enforce permissions, and choose an execution path.
3. On-device models: language, vision, speech, ranking, and other specialized models that can execute locally.
4. Private Cloud Compute: larger Apple models for requests that exceed the local path’s capability or resource envelope.
5. External model integrations: a separate, optional path such as ChatGPT, used only in supported experiences and subject to user controls. ⁴⁵¹⁷

This distinction matters. It is accurate to say that Apple Intelligence has extensive on-device processing. It is inaccurate to claim that the entire system always runs locally.

The diagram separates on-device models, system orchestration, Private Cloud Compute, and an optional external service such as ChatGPT. Apple's complete per-request routing policy is not public; the PCC documentation describes the server-side path.

What does “Apple Intelligence local LLM” mean?

The search phrase can refer to three very different systems.

Apple’s operating-system foundation model

Apple ships and manages an on-device model as part of the OS. Apple Intelligence and the Foundation Models framework can use it without an app bundling its own multi-gigabyte weights. Developers receive an API, not an unrestricted copy of the production model weights. Apple controls updates, compression, safety behavior, language availability, and hardware compatibility. ⁷⁹

Publicly documented Apple Foundation Models

Apple publishes research articles and technical reports describing model families, optimization techniques, evaluations, and safety work. Those reports improve transparency, but they do not turn the production Apple Intelligence models into downloadable open-weight releases. ⁶⁷¹⁸

User-installed open models on a Mac

A Mac owner can separately run Llama, Qwen, Mistral, Gemma, or other open models through MLX, llama.cpp, Core ML, or third-party applications. These deployments can offer user-selected context windows, sampling parameters, retrieval pipelines, adapters, and private local endpoints. They do not automatically become Siri’s model or gain Apple Intelligence’s privileged operating-system context. ¹⁴¹⁵

Apple’s on-device model architecture

The 2025 on-device model

Apple’s 2025 foundation-model report describes a multilingual and multimodal on-device language model with approximately 3 billion parameters. It was optimized for Apple silicon using quantization-aware training. Apple reported roughly 2-bit main weights, a 4-bit embedding table, and an 8-bit KV cache in the documented configuration. ⁷

The model also used KV-cache sharing between transformer blocks. Apple reported a 37.5% reduction in KV-cache memory and a similar reduction in time to first token for the evaluated architecture. These are model-design results from Apple’s report, not a universal benchmark for every iPhone, iPad, or Mac. ⁷

For visual understanding, the 2025 on-device family used an approximately 300-million-parameter ViTDet-L-based encoder, while the server family used a larger visual encoder. ⁷

Apple positioned the small system model for focused tasks such as summarization, extraction, text understanding, rewriting, short conversations, and tool-assisted app workflows. The report explicitly does not support treating it as a full replacement for a large, knowledge-heavy cloud chatbot. ⁷

Apple Foundation Models 3 in 2026

On June 8, 2026, Apple announced a five-model family created in collaboration with Google: ⁶

Model	Execution location	Apple’s stated role	Status on July 22, 2026
AFM 3 Core	On-device	next-generation dense 3B system model	preview/beta for the 27-generation platforms
AFM 3 Core Advanced	On-device	sparse, native multimodal model; 20B total and 1–4B active	reserved for Apple’s most capable silicon systems
AFM 3 Cloud	Private Cloud Compute	fast and efficient server workhorse	preview/beta
ADM 3 Cloud (Image)	Private Cloud Compute	image generation, editing, and Genmoji	preview/beta
AFM 3 Cloud Pro	Extended PCC	complex reasoning and agentic tool use	gradual summer-preview rollout

AFM 3 Core Advanced addresses a central constraint of consumer-device inference: keeping a large model’s full weights in DRAM. Apple says the full expert set is stored in NAND flash. A lightweight dense routing block chooses a fixed group of experts during initial prompt processing and periodically reselects experts during generation. Shared experts remain active while routed experts are loaded only when needed. ⁶

This is not conventional flash swapping on every generated token. Apple designed the router specifically to avoid the bandwidth cost of standard token-level mixture-of-experts loading. The result is a model with 20 billion total parameters but a much smaller active parameter set for any one request.

What Apple has not disclosed

Apple has not published a durable production table containing:

• the general system model’s exact context window,
• per-model download sizes,
• peak and steady-state RAM use by feature,
• token-per-second results for each supported chip,
• a complete operator map across CPU, GPU, and Neural Engine,
• the full automatic routing policy between local, PCC, and external models.

A WWDC 2026 developer session describes a 32K-token context for the PCC model exposed through that developer workflow. It should not be generalized to every Apple Intelligence model or consumer feature. ¹¹

Supported devices and hardware requirements

Current baseline support

Apple’s July 7, 2026 support document lists the following baseline: ¹

Product category	Supported hardware	Minimum software	Additional requirement
iPhone	iPhone 15 Pro/Pro Max; iPhone 16 family or later	iOS 18.1 or later	7 GB storage; device and Siri languages must match and be supported
iPad	iPad mini with A17 Pro; iPads with M1 or later	iPadOS 18.1 or later	7 GB storage
Mac	any Mac with Apple silicon	macOS Sequoia 15.1 or later	7 GB storage
Apple Vision Pro	supported Vision Pro hardware	visionOS 2.4 or later	regional and language limits apply
Apple Watch	Series 6+, all Ultra models, SE 2+	watchOS 11 or later	must be paired with a nearby Apple-Intelligence-capable iPhone

Apple Watch support should not be read as proof that the same foundation models run entirely on the watch. Apple explicitly requires a compatible paired iPhone, and individual features can depend on that phone. ¹

Higher requirements for selected 2026 capabilities

Apple attaches stricter hardware notes to several 27-generation features. For example, selected new Siri voice and higher-accuracy dictation capabilities require devices such as iPhone 17 Pro/Pro Max or iPhone Air, M4-class iPads with at least 12 GB unified memory, or M3-class Macs with at least 12 GB unified memory. These are feature-specific requirements, not a replacement for the general Apple Intelligence compatibility list. ²

Support does not mean that every model runs locally on every device. Apple is creating tiers inside the supported-device family: a device may support Apple Intelligence and the compact AFM 3 Core path while lacking the memory, bandwidth, or thermal budget for AFM 3 Core Advanced. There is no single published formula that maps chip specifications to model access; eligibility is documented at the feature level.

The diagram separates baseline Apple Intelligence compatibility from higher hardware requirements for selected 2026 features; Apple lists those thresholds in its support documentation.

Which Apple Intelligence features run on-device?

There is no complete public feature-to-model matrix. The same interface can use a different route depending on request complexity, device generation, language, software version, and user choice. The conservative table below avoids turning marketing categories into unsupported execution claims.

Feature or execution path	On-device	PCC	External service	Evidence-based assessment
Foundation Models framework with the system on-device model	yes	no for this explicitly selected path	no	Apple describes it as embedded in the OS and available offline. 9
Summarization, extraction, and rewriting through that local framework path	yes	only if the app chooses another provider	possible through the provider protocol	The app’s selected model is the deciding factor. 91011
Writing Tools in system apps	often	possible for harder tasks	ChatGPT can be used for Compose or an explicit integration	Apple does not guarantee that every Writing Tools request uses one fixed local model. 15
Mail, Messages, and notification summaries	possible	possible	not normally needed	The features are documented; the per-request execution map is not. 13
Siri	partly	yes for complex requests	ChatGPT with consent/configuration	Siri is an orchestrator and interface, not one model. 25
Live Translation	Apple highlights on-device execution for key paths	future implementations may vary	not normally	Offline and privacy benefits are official; the full model chain is feature- and device-dependent. 19
Genmoji	model- and version-dependent	the 2026 ADM 3 Cloud model can power Genmoji	not normally	It should not be labeled universally local. 6
Image Playground	earlier/lightweight styles can use local components	2026 high-quality and photorealistic generation uses PCC	separate ChatGPT image generation may be offered	The selected style and OS version matter. 610
2026 enhanced dictation	local on listed high-end devices	not for Apple’s stated on-device path	no	AFM 3 Core Advanced is explicitly an on-device model. 26
Visual intelligence	local preprocessing can occur	Apple server paths can occur	ChatGPT and Google Search can be deliberately invoked	The action selected by the user determines the data flow. 1
Shortcuts “Use Model” action	selectable	selectable	ChatGPT selectable	This is one of Apple’s clearest explicit model-routing controls. 20

Why a permanent local-versus-cloud checklist would be misleading

Apple Intelligence is task-oriented. “Summarize” may refer to a short email, a long set of notes, an image-plus-text request, or one step in an agentic workflow. The visible feature name therefore does not uniquely identify the model.

A reproducible test should record:

• device and chip,
• OS build,
• language and region,
• app and feature,
• whether networking was available,
• any visible model selection,
• input length and modality.

Without those details, a statement such as “Genmoji is local” or “Siri uses the cloud” is too broad to remain accurate across platform generations.

The flow shows minimization before a request enters an on-device or PCC route; only task-relevant context should enter the selected route. Apple's PCC architecture describes the server-side path.

How does Apple choose between local processing and PCC?

Apple’s public description is high-level: process on-device when possible; use a larger PCC model when the request requires more capability. ⁴¹⁶

Apple has not published the full dispatcher. The following factors are technically plausible but should not be presented as the complete internal algorithm:

• capability and modality required,
• context size and task complexity,
• which model tier the device supports,
• available memory, power, and thermal state,
• language support,
• safety or policy requirements,
• explicit user or developer selection.

For PCC, the device can verify that the destination is running an approved, publicly attested software image. The request is encrypted to an eligible PCC node. Apple also describes relay and privacy mechanisms intended to prevent the inference service from directly linking an IP address to request content. ⁴

The decision tree shows the possible local, PCC, and external routes; Apple does not publish the exact internal thresholds.

Private Cloud Compute architecture

PCC is Apple’s attempt to extend some of the device’s privacy properties to server-scale inference. Apple defined five core requirements: ⁴

1. Stateless user-data processing: request data must not be retained after the response.
2. Enforceable guarantees: privacy must be implemented in hardware and software rather than relying only on policy.
3. No privileged runtime access: administrators must not have a special data-access path into production inference.
4. Non-targetability: attackers should not be able to route one user to a specially modified node.
5. Verifiable transparency: researchers should be able to inspect the software associated with production deployments.

Original PCC nodes

Apple’s 2024 design used Apple silicon, Secure Enclave, Secure Boot, a hardened operating-system subset, strict code signing, and a minimal runtime surface. Apple says the production environment avoids general-purpose remote shells and conventional logging paths that could expose user request data. Public transparency records and published software artifacts allow devices and researchers to verify deployment claims. ⁴

PCC expansion to Google Cloud and NVIDIA GPUs

In June 2026, Apple announced that the most demanding Apple Intelligence workloads could run on NVIDIA GPUs in Google Cloud under an expanded PCC model. Apple cites NVIDIA Confidential Computing, Intel TDX, Google Titan, independent trust roots, attested keys, an append-only ledger, and published binaries as elements of the new chain of trust. The capacity was being introduced gradually during the summer preview. ⁸

This changes an important architectural assumption. PCC no longer means only Apple-silicon servers in Apple-owned data centers. Apple’s position is that the same privacy requirements can be maintained through a multi-party confidential-computing design. That claim is official; the architecture should still be evaluated through ongoing independent security research as deployment matures.

The security diagram shows encrypted requests, attested software, stateless processing, and public transparency artifacts described by Apple Security Research.

Privacy models: on-device, PCC, and ChatGPT are not equivalent

Route	Processing location	Model operator	Retention claim	User control
On-device system model	iPhone, iPad, or Mac	Apple’s OS model	inference input need not leave the device	sometimes implicit; explicit in developer APIs
Private Cloud Compute	attested PCC environment; in 2026 potentially extended Google Cloud infrastructure	Apple-controlled PCC software	request data is not stored after processing, according to Apple	automatic routing or explicit PCC selection
ChatGPT integration without an account	OpenAI infrastructure	OpenAI	Apple and OpenAI state that requests are not stored for this integration and IP addresses are obscured	confirmation before sharing; extra approval for files/photos
ChatGPT with an account	OpenAI infrastructure	OpenAI	account settings and OpenAI policies apply	user deliberately signs in
Self-hosted MLX or llama.cpp model	the user’s Mac	user/model publisher	local unless the app adds telemetry or network tools	fully configurable by the user

Apple says users are asked before information is sent to ChatGPT, and photos or files require confirmation. The integration can be used without an account; signing in changes the governing data settings. ⁵¹⁷

“Local” is not by itself a complete privacy audit. A local third-party app can log prompts, send analytics, or call remote tools. Conversely, PCC is cloud inference but uses a materially different security architecture from a typical hosted LLM API.

The comparison separates on-device processing, Private Cloud Compute, and conventional cloud AI by location, operator, retention, and user control.

Neural Engine, CPU, GPU, and unified memory

Apple silicon combines multiple compute engines. Their general roles are documented, but Apple does not disclose the exact operator placement for every internal Apple Intelligence model.

Component	Typical strength	Official platform role	Important caveat
CPU	control flow, tokenization, small operations, app/system logic	Core ML and Core AI can use the CPU	no public full operator map for Apple Intelligence
GPU	highly parallel matrix operations, local LLMs, image models	Metal, MLX, and Core ML can use GPU compute	actual use depends on runtime and model graph
Neural Engine	power-efficient supported ML operations	Core ML and Core AI can target the Neural Engine	not every LLM operator or framework automatically executes there
Unified memory	shared address space for CPU/GPU and other system components	MLX explicitly exploits Apple’s unified-memory architecture	shared does not mean unlimited; capacity and bandwidth remain constraints
NAND flash	persistent model storage	AFM 3 Core Advanced stores its full expert set in NAND	flash is not a substitute for active DRAM; selected experts are loaded into memory

Core ML can schedule supported workloads across CPU, GPU, and Neural Engine. Core AI, introduced in the 2026 platform generation, provides broader building blocks for generative AI. MLX uses unified memory so arrays do not require explicit copying between separate CPU and GPU memory pools. ^12131421

The stack shows how Apple Intelligence apps connect through the Foundation Models framework to models, compute engines, and memory; Apple's exact internal scheduling is not public.

How a local language model runs on Apple silicon

A simplified text-generation request involves:

1. tokenizing the input,
2. loading or activating model weights,
3. processing the prompt during the prefill phase,
4. building a KV cache for previous tokens,
5. generating output autoregressively,
6. detokenizing and passing the result through application and safety logic.

AFM 3 Core Advanced adds expert routing. The full expert library remains in flash, while selected experts are assembled into the active in-memory model for the prompt and can be periodically changed during generation. ⁶

Apple Foundation Models framework for developers

The Foundation Models framework is Apple’s native API for using the system model. In its 2025 form, it exposed the roughly 3B on-device model through Swift. An app does not need to ship the base weights, and the on-device route is designed to work offline. ⁹

Apple identifies good use cases such as:

• summarization,
• structured information extraction,
• text comprehension,
• rewriting and refinement,
• short-form dialogue,
• creative short content,
• app-specific workflows that call tools. ⁷⁹

The system model should not be treated as a universal source of current world knowledge. Narrow prompts, app-provided tools, retrieval from trusted local data, and schema-constrained output are safer design patterns.

Core API concepts

• LanguageModelSession: maintains state and coordinates requests.
• Guided Generation: returns typed Swift structures from a schema.
• Tool Calling: allows the model to invoke controlled application functions.
• Streaming snapshots: delivers progressively completed structured output.
• Availability and guardrails: lets an app check model, language, and restriction status.
• Adapters: version-specific LoRA adapters can specialize behavior but consume storage and require lifecycle management. ⁷⁹

2026 framework expansion

Apple’s WWDC 2026 material describes: ^10112223

• combined image and text input for the on-device system model,
• a broader LanguageModel and executor protocol,
• support for custom local and hosted model providers,
• planned Swift packages or integrations from vendors including Anthropic and Google,
• Dynamic Profiles,
• model and feature evaluation tools,
• an fm command-line tool and Python SDK on macOS 27,
• access to a PCC model for approved developers, subject to entitlements and quotas.

The result is closer to a model abstraction layer than a single local API. That flexibility creates a disclosure responsibility: applications should clearly indicate whether a request stays on-device, uses PCC, or goes to a third-party provider.

The diagram shows an app connecting through the Foundation Models framework to Apple's local system model, PCC, or an external provider protocol; see Apple's WWDC 2026 documentation.

Foundation Models framework vs Core ML, Core AI, MLX, and llama.cpp

Technology	Primary purpose	Model source	Typical compute	Can be offline?	Relationship to Apple Intelligence
Foundation Models framework	Apple system model and unified model API	Apple system model; 2026 PCC/providers	system-managed	yes for on-device route	direct
Core ML	deploy converted ML models in Apple apps	developer-provided	CPU, GPU, Neural Engine	yes	general ML layer, not the Apple Intelligence product
Core AI	native generative-AI and modern model pipelines	developer/platform	CPU, GPU, Neural Engine	model-dependent	complements system and custom model paths
MLX	research, fine-tuning, and flexible local inference on Apple silicon	community or self-trained	mainly CPU/GPU with unified memory	yes	separate from Apple Intelligence
llama.cpp	portable inference for quantized GGUF models	community	CPU/GPU with Metal support	yes	separate

Practical selection guide

• Choose the Foundation Models framework for private, narrow language tasks that benefit from a system-managed model and native Swift tooling.
• Choose Core ML when you need to ship or convert a specific model and control its app deployment; conversion typically runs through Core ML Tools.²⁴
• Choose Core AI for Apple-native generative pipelines and newer model abstractions.
• Choose MLX for Python-oriented research, fine-tuning, evaluation, and rapid local experimentation on a Mac.
• Choose llama.cpp for broad GGUF compatibility, portable local servers, and highly quantized community models.

Apple Intelligence vs a traditional local LLM on Mac

Criterion	Apple Intelligence	User-installed local LLM
Setup	OS-managed	user installs runtime and weights
OS context	deep, permission-controlled system integration	only data explicitly exposed by the app or user
Model choice	mostly controlled by Apple; some routes selectable	fully selectable
Customization	prompting, tools, typed output, limited adapters	system prompts, sampling, RAG, LoRA/fine-tuning, model swaps
Offline operation	available for many paths	available if no cloud tools are enabled
Cloud fallback	PCC or optional partner integration	only if the user configures one
Transparency	detailed papers, but closed production weights	varies by model card, training disclosure, and license
Maintenance	OS updates	user manages versions and storage

Apple Intelligence optimizes for low friction and operating-system integration. A self-hosted model optimizes for control, reproducibility, experimentation, and model choice.

Apple vs Google, Microsoft, and Samsung on-device AI

All major platform vendors now use hybrid architectures. The relevant differences are model management, developer APIs, hardware requirements, and cloud trust boundaries.

Platform	Local AI layer	Cloud/hybrid route	Developer surface	Distinguishing approach
Apple	Apple Foundation Models in the OS; Core ML/Core AI	Private Cloud Compute; optional partner models	Foundation Models framework, Core ML, Core AI, MLX	attested PCC architecture and deep native-app integration
Google/Android	Gemini Nano managed through AICore; ML Kit GenAI	Gemini cloud services and app APIs	ML Kit GenAI, LiteRT/LiteRT-LM, Gemini APIs	AICore manages supported on-device models and updates
Microsoft/Windows	local Windows AI components on Copilot+ PCs	Copilot and Azure services	Windows AI APIs, ONNX Runtime, DirectML	NPU-focused Copilot+ class with a 40+ TOPS platform threshold
Samsung Galaxy AI	mix of device-resident and cloud features	Samsung and partner services	primarily Galaxy/Android application surfaces	a device setting can prioritize on-device processing for supported features

Google documents Gemini Nano as an AICore-managed system service and exposes task-focused ML Kit GenAI APIs. Microsoft combines local NPU-backed Windows AI components with cloud Copilot experiences. Samsung distinguishes on-device and cloud-based Galaxy AI capabilities and offers a local-only preference on supported devices, with feature trade-offs. ^252627282930

No vendor is categorically “faster” or “more private” for every workload. A fair comparison must specify device, task, network state, model version, data path, and whether the result comes from vendor-run or independent evaluation.

Performance, storage, memory, and energy constraints

Officially documented facts

• Apple Intelligence currently requires 7 GB of storage on compatible iPhone, iPad, and Mac devices. ¹
• The 2025 on-device model uses aggressive quantization and KV-cache optimization. ⁷
• AFM 3 Core Advanced stores full weights in NAND and activates 1–4B parameters for a request. ⁶
• Selected 2026 advanced capabilities require at least 12 GB of unified memory on specified iPad and Mac configurations. ²

Numbers Apple has not supplied

No reliable consumer table of system-model tokens per second by chip exists. Such a figure would depend on prompt length, output length, thermal state, active expert count, memory pressure, tool calls, model build, and decoding configuration.

The 7 GB requirement is also not a simple model-file size. It can cover multiple language, image, audio, safety, and support resources. Likewise, multiplying parameter count by quantization bits would not yield an exact download or RAM requirement: embeddings, metadata, adapters, runtime buffers, KV cache, and activations add overhead.

Chip-generation effects

Newer Apple silicon can improve memory bandwidth, GPU and Neural Engine throughput, power efficiency, and available unified-memory capacity. However, Apple grants advanced local features by supported-device list rather than publishing a universal performance formula. An M1 Mac remains compatible with Apple Intelligence but should not be assumed to run every AFM 3 Core Advanced workload announced for higher-tier 2026 hardware. ¹²

Best use cases for Apple on-device AI

Strong local workloads

• summarizing short private documents or messages,
• extracting dates and structured fields,
• rewriting and tone adjustment,
• classification and prioritization,
• app-specific tool selection,
• compact assistants with bounded context,
• supported on-device speech and audio tasks.

Workloads more likely to need larger models

• complex multi-step reasoning,
• very long or richly multimodal contexts,
• large agentic tool chains,
• high-quality or photorealistic image generation,
• tasks requiring current web knowledge or broad external retrieval.

These are not absolute boundaries. A small model with constrained output and reliable tools can outperform a larger general model on a narrow workflow. A local execution path also does not eliminate hallucination or guarantee factual accuracy.

Advantages and limitations

Advantages

• low latency for suitable local tasks,
• offline operation,
• reduced data transfer,
• deep app and OS integration,
• system-managed weights without inflating every app bundle,
• native Swift APIs with typed output,
• a formalized privacy architecture for server fallback through PCC.

Limitations

• device, language, and regional fragmentation,
• closed production weights,
• limited world knowledge in the compact model,
• incomplete visibility into automatic routing,
• some features require networking or newer hardware,
• model and adapter behavior can change with OS releases,
• external integrations use separate policies and trust boundaries,
• Apple’s first-party evaluations are not substitutes for independent benchmarks.

Development status as of July 22, 2026

The stable reference point is the iOS 26, iPadOS 26, and macOS Tahoe 26 feature set. The 27-generation platform introduces Apple Foundation Models 3, a redesigned Siri architecture, stronger local audio capabilities, new PCC models, higher-end Image Playground output, and broader developer tooling. ¹²⁶¹⁰

Three caveats are essential:

1. Final public releases of the 27-generation operating systems were not broadly available on July 22, 2026.
2. Apple said a fuller technical report for AFM 3 would arrive later in summer 2026. ⁶
3. The Google Cloud/NVIDIA expansion of PCC was still ramping during the summer preview. ⁸

Performance, routing, and device-eligibility statements for the 27-generation features should therefore be rechecked after the final software release and the promised technical report.

The future of local AI on Apple devices

Apple’s 2026 architecture points to three longer-term developments:

• larger local models without full DRAM residency: prompt-level expert selection turns NAND into a model-capacity tier while keeping the active working set smaller;
• a common developer abstraction: Apple’s system model, PCC, and third-party models can be exposed through compatible protocols;
• more confidential cloud capacity: PCC expands from homogeneous Apple-silicon servers toward heterogeneous hardware and partner data centers.

The strategic question is no longer simply “local or cloud?” It is: which data reaches which model, under which verifiable trust boundary, for what purpose? Developers will need to treat data minimization, route disclosure, evaluation, fallback behavior, and permission design as core product features.

Conclusion: Hybrid on-device models plus Private Cloud Compute

Apple Intelligence is a hybrid on-device and private-cloud system, not one local LLM. Apple combines compact and increasingly capable device models with Private Cloud Compute and optional external providers. The progression from a quantized 3B model to AFM 3 Core Advanced demonstrates a practical route to larger local AI through sparse experts, NAND-backed capacity, and hardware-tiered activation. ⁶⁷

The most useful question is not merely whether a feature is “local.” It is: which model handles which data, where does it execute, and what storage, permission, and verification rules apply? Apple provides unusually detailed research and PCC security documentation. Even so, its complete feature-routing matrix, per-device memory use, and real-world model performance remain only partly disclosed.

Sources

The product-status snapshot remains July 22, 2026. The architectural descriptions and image captions were checked against the linked Apple documentation on August 15, 2026.

What remains unknown

• Apple’s exact automatic routing thresholds between on-device, PCC, and external providers are not public.
• A permanent matrix assigning every user-facing feature to one production model has not been published.
• Exact RAM use, individual model download size, and tokens per second by device are not disclosed.
• The complete operator placement of internal models across CPU, GPU, and Neural Engine is not documented.
• The 32K context cited in a WWDC 2026 session applies to the described developer PCC route and was not generalized to all system models.
• Final availability and performance of iOS 27/macOS 27 capabilities may change before general release.
• No numerical thermal or energy comparison by Apple chip was included because Apple has not published a directly comparable official dataset.
• Rumors about unreleased chips, model sizes, or dates were excluded.

Footnotes

1. How to get Apple Intelligence. Apple Support, published July 7, 2026. Support documentation. Supports device, OS, 7 GB storage, language, region, and stable feature claims. https://support.apple.com/en-us/121115 ↩ ↩² ↩³ ↩⁴ ↩⁵ ↩⁶ ↩⁷ ↩⁸ ↩⁹ ↩¹⁰

2. Apple Intelligence and Siri. Apple, continuously updated product page, July 2026 snapshot. Product and availability documentation. Supports 2026 feature announcements, device footnotes, and preview status. https://www.apple.com/apple-intelligence/ ↩ ↩² ↩³ ↩⁴ ↩⁵ ↩⁶ ↩⁷

3. Apple Intelligence brings powerful AI capabilities into everyday experiences. Apple Newsroom, June 8, 2026. Press release. Supports operating-system integration and next-generation feature scope. https://www.apple.com/newsroom/2026/06/apple-intelligence-brings-powerful-ai-capabilities-into-everyday-experiences/ ↩ ↩² ↩³ ↩⁴

4. Private Cloud Compute: A new frontier for AI privacy in the cloud. Apple Security Research, June 10, 2024. Security architecture. Supports PCC requirements, attestation, data processing, and transparency. https://security.apple.com/blog/private-cloud-compute/ ↩ ↩² ↩³ ↩⁴ ↩⁵ ↩⁶ ↩⁷ ↩⁸

5. Use ChatGPT with Apple Intelligence on iPhone. Apple Support, continuously updated. User documentation. Supports consent, photo/file confirmation, and account behavior. https://support.apple.com/guide/iphone/use-chatgpt-with-apple-intelligence-iph00fd3c8c2/ios ↩ ↩² ↩³ ↩⁴ ↩⁵ ↩⁶

6. Introducing the Third Generation of Apple’s Foundation Models. Apple Machine Learning Research, June 8, 2026. Official architecture/research article. Supports AFM 3 model names, parameter counts, sparse routing, NAND/DRAM design, training, and preview status. https://machinelearning.apple.com/research/introducing-third-generation-of-apple-foundation-models ↩ ↩² ↩³ ↩⁴ ↩⁵ ↩⁶ ↩⁷ ↩⁸ ↩⁹ ↩¹⁰ ↩¹¹ ↩¹² ↩¹³

7. Apple Intelligence Foundation Language Models: Tech Report 2025. Apple, revised August 27, 2025. Technical report/paper. Supports the 3B on-device model, quantization, KV-cache sharing, model use cases, and adapters. https://machinelearning.apple.com/papers/apple_intelligence_foundation_language_models_tech_report_2025.pdf ↩ ↩² ↩³ ↩⁴ ↩⁵ ↩⁶ ↩⁷ ↩⁸ ↩⁹ ↩¹⁰ ↩¹¹

8. Expanding Private Cloud Compute. Apple Security Research, June 8, 2026. Security architecture/preview. Supports Google Cloud and NVIDIA GPU expansion and the revised chain of trust. https://security.apple.com/blog/expanding-pcc/ ↩ ↩² ↩³

9. Meet the Foundation Models framework. Apple Developer, WWDC 2025. Technical session. Supports the on-device system model, Swift API, Guided Generation, Tool Calling, and offline operation. https://developer.apple.com/videos/play/wwdc2025/286/ ↩ ↩² ↩³ ↩⁴ ↩⁵ ↩⁶ ↩⁷

10. WWDC26 Apple Intelligence guide. Apple Developer, June 2026. Developer overview. Supports 2026 framework, Image Playground, and platform changes. https://developer.apple.com/wwdc26/guides/apple-intelligence/ ↩ ↩² ↩³ ↩⁴ ↩⁵

11. Bring your large language model to the Foundation Models framework. Apple Developer, WWDC 2026. Technical session. Supports the LanguageModel/executor protocol, third-party routes, and the developer PCC context statement. https://developer.apple.com/videos/play/wwdc2026/339/ ↩ ↩² ↩³ ↩⁴

12. Core ML. Apple Developer Documentation, continuously updated. Framework documentation. Supports CPU, GPU, and Neural Engine execution. https://developer.apple.com/documentation/coreml/ ↩ ↩²

13. Core AI. Apple Developer Documentation, 2026. Framework documentation. Supports Apple’s generative-AI and model-pipeline platform. https://developer.apple.com/documentation/coreai ↩ ↩²

14. MLX. Apple Machine Learning Research, GitHub, continuously updated. Official open-source repository. Supports MLX’s purpose and Apple-silicon optimization. https://github.com/ml-explore/mlx ↩ ↩² ↩³

15. llama.cpp. ggml-org, GitHub, continuously updated. Official open-source repository. Supports local GGUF inference and Metal acceleration on Apple silicon. https://github.com/ggml-org/llama.cpp ↩ ↩²

16. Introducing Apple Intelligence, the personal intelligence system. Apple Newsroom, June 10, 2024. Press release. Supports the original product definition and hybrid architecture. https://www.apple.com/newsroom/2024/06/introducing-apple-intelligence-for-iphone-ipad-and-mac/ ↩ ↩²

17. OpenAI and Apple announce partnership. OpenAI, June 10, 2024. Official provider announcement. Supports privacy handling for the no-account Apple integration. https://openai.com/index/openai-and-apple-announce-partnership/ ↩ ↩²

18. Introducing Apple’s On-Device and Server Foundation Models. Apple Machine Learning Research, June 10, 2024. Official research article. Supports the first publicly described Apple Intelligence model generation and specialization. https://machinelearning.apple.com/research/introducing-apple-foundation-models ↩

19. Apple Intelligence gets even more powerful with new capabilities across Apple devices. Apple Newsroom, June 9, 2025. Press release. Supports Live Translation, developer access, and 2025 platform features. https://www.apple.com/newsroom/2025/06/apple-intelligence-gets-even-more-powerful-with-new-capabilities-across-apple-devices/ ↩

20. Use Apple Intelligence models in Shortcuts on iPhone. Apple Support, continuously updated. User documentation. Supports explicit selection of On-Device, PCC, or ChatGPT in Shortcuts. https://support.apple.com/guide/iphone/use-apple-intelligence-in-shortcuts-iph78c41eaf8/ios ↩

21. Unified Memory in MLX. Apple MLX Documentation, continuously updated. Technical documentation. Supports the shared CPU/GPU memory model used by MLX. https://ml-explore.github.io/mlx/build/html/usage/unified_memory.html ↩

22. Use the Foundation Models framework from the command line. Apple Developer, WWDC 2026. Technical session. Supports the fm CLI and Python SDK on macOS 27. https://developer.apple.com/videos/play/wwdc2026/334/ ↩

23. Access the cloud model with the Foundation Models framework. Apple Developer, WWDC 2026. Technical session. Supports developer PCC access, eligibility, and quotas. https://developer.apple.com/videos/play/wwdc2026/319/ ↩

24. Core ML Tools overview. Apple, continuously updated. Developer documentation. Supports model conversion and ML Program deployment. https://apple.github.io/coremltools/docs-guides/source/overview-coremltools.html ↩

25. Gemini Nano. Android Developers, continuously updated. Platform documentation. Supports AICore-managed on-device Gemini Nano. https://developer.android.com/ai/gemini-nano ↩

26. AI on Android. Android Developers, continuously updated. Platform overview. Supports local and cloud AI developer routes. https://developer.android.com/ai/overview ↩

27. NPU devices / Copilot+ PCs. Microsoft Learn, continuously updated. Platform documentation. Supports the Copilot+ NPU class and requirements. https://learn.microsoft.com/en-us/windows/ai/npu-devices/ ↩

28. Windows Copilot AI components. Microsoft Support, continuously updated. Product support. Supports local Windows AI components. https://support.microsoft.com/topic/windows-copilot-ai-components-a9ef14e9-32a7-497f-b780-7b6fb63af793 ↩

29. Galaxy AI. Samsung, continuously updated product page. Product documentation. Supports the Galaxy AI feature family. https://www.samsung.com/us/galaxy-ai/ ↩

30. On-device and cloud-based Galaxy AI functions. Samsung Support, continuously updated. Support documentation. Supports the local/cloud distinction and device-processing preference. https://www.samsung.com/ae/support/mobile-devices/how-to-distinguish-between-on-device-functions-and-cloud-based-functions-among-new-ai-features/ ↩