Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Apple / Apple Foundation Models 2025

AFM Server (2025)

Second-generation multimodal Apple foundation model. Model-level image capability is distinct from what the original developer framework exposed.

Language models (LLMs)
historicalClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
9 of 20 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesApple Private Cloud Compute (2025 reference)
Output billingSee billing notesAccess and billing notes below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
SupportedSource for Tool calling (opens in a new tab)

Documented tool-use training and evaluations; server public API access is not implied.

Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2025-06-09Source for Release date (opens in a new tab)

Generation announcement.

Parameters
Not collected
Architecture
Parallel-Track Mixture-of-Experts; three 4,096-window local layers followed by one global-attention layerSource for Architecture (opens in a new tab)
Languages
16 languages in technical report; overview says 15Source for Languages (opens in a new tab)

Preserve the source discrepancy. Supported-language count is not a promise that every feature supports every locale.

Context caching
Not collected
Quantization and compression
3.56-bit ASTC decoder compression; 4-bit embeddings; 8-bit KV cacheSource for Quantization and compression (opens in a new tab)
Vision encoder
1B-parameter ViT-gSource for Vision encoder (opens in a new tab)

Component size, not the language decoder or total model size.

Published price
Apple product integration; standalone server inference rate not verifiedSource for Published price (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Apple Private Cloud Compute (2025 reference)

Provider source (opens in a new tab)
API model ID
Not collected

Product or SDK model identity, not a verified public HTTP model selector.

Access
Integrated server generation. The later OS 27 SDK is not backdated onto this checkpoint.
Regions
Supported Apple devices, OS versions, languages and regions only. A device-local model is not a guarantee of access in every market.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Apple Private Cloud Compute (2025 reference)

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

MMLU

Apple · vendor-reported
80.2%

Apple technical report Tables 1–2, instruct/non-thinking models and Simple-Evals on supported languages. These are paper model results, not guaranteed scores for the compressed installed OS build.

Evaluation source (opens in a new tab)

MMMLU

Apple · vendor-reported
74.6%

Apple technical report Tables 1–2, instruct/non-thinking models and Simple-Evals on supported languages. These are paper model results, not guaranteed scores for the compressed installed OS build.

Evaluation source (opens in a new tab)

MGSM

Apple · vendor-reported
87.09%

Apple technical report Tables 1–2, instruct/non-thinking models and Simple-Evals on supported languages. These are paper model results, not guaranteed scores for the compressed installed OS build.

Evaluation source (opens in a new tab)

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Apple documents this proprietary product model. No matching unrestricted public checkpoint was verified in the reviewed Apple weight inventory. Closed-weight classification is inferred for this product identity; OS delivery and member-gated model assets do not imply an open-weight release.

Classification evidence (opens in a new tab)

Lifecycle dates

Generation announced9 Jun 2025Source (opens in a new tab)

Sources reviewed