---
id: 1488
title: "Understanding Apple’s On-Device and Server Foundation Models release"
source_domain: blog.trailofbits.com
source_url: "https://blog.trailofbits.com/2024/06/14/understanding-apples-on-device-and-server-foundations-model-release/"
published_at: "2024-06-14 20:49"
tags: ["ai-security", "cloud", "llm", "apple", "machine-learning", "wwdc", "on-device-ai", "foundation-models"]
phying_url: "https://phying.com/item/1488"
lang: en
---

# Understanding Apple’s On-Device and Server Foundation Models release

## Summary

Trail of Bits dissects Apple's WWDC foundation models: five models with LoRA/DoRA adapters, a ~3B on-device LLM, server inference on Apple Silicon, and a deliberate NVIDIA/CUDA-free ML stack.

## Intelligence Metadata

- **Sources:** blog.trailofbits.com
- **Published:** 2024-06-14 20:49
- **Original:** https://blog.trailofbits.com/2024/06/14/understanding-apples-on-device-and-server-foundations-model-release/
- **Phying News:** https://phying.com/item/1488