By Mirai Labs, frontier on-device AI lab. Building the models, inference runtime, and quantization stack from the device constraint up.
Part 4: Brief history of Apple ML Stack
By Mirai Labs, frontier on-device AI lab. Building the models, inference runtime, and quantization stack from the device constraint up.
Mirai Labs: Frontier On-Device AI Lab
Models, runtime & infrastructure to make on-device AI interactive, ambient & continuous.
Introducing Pipette: A benchmarking suite for on-device intelligence — Blog
Meet Pipette, an open-source platform for reproducible on-device AI benchmarks across models, quantization, runtimes and hardware.
On-device intelligence for every product
We're building a frontier lab for on-device AI. Small, specialized models for audio, vision, and text, faster than the cloud and free.
Melange | On-device AI for Mobile
Select. Benchmark. Deploy | End-to-end on-device AI deployment tool for mobile devs.
We Melted iPhones for Science
OASIS generated real-time video with on-device AI. Four years later, Apple redesigned the iPhone so that AI won't burn your hand -- and admitted that we were right.
Introducing Apple’s On-Device and Server Foundation Models
At the 2024 Worldwide Developers Conference, we introduced Apple Intelligence, a personal intelligence system integrated deeply into iOS 18…
Locally AI - Run AI models locally on your iPhone, iPad, and Mac.
Run Llama, Gemma, Qwen, DeepSeek, and more on your iPhone, iPad, and Mac. Optimized for Apple Silicon. Offline. Private.
ZETIC | On-Device AI for Everything - for any model, on any device, in any framework
Built by ex-Qualcomm AI Engineer. Automate on-device AI deployment with full NPU optimization. Benchmark on 100+ physical devices and ship in hours with just 3 lines of code.
Models on-device | Ai2
Ai2, a non-profit research institute founded by Paul Allen, is committed to breakthrough AI to solve the world’s biggest problems.
Artificial Analysis on Twitter / X
We benchmarked Apple's new On-Device model: trails most Gemma and Qwen on-device suitable models but still very usefulGPQA Diamond performance trailed models that are suitable for on-device use such as the smaller Gemma models (3n E4B, 4B, 12B) and Qwen3 models (1.7B, 4B, 8B).… pic.twitter.com/wMrNM7yinL— Artificial Analysis (@ArtificialAnlys) June 20, 2025
Updates to Apple’s On-Device and Server Foundation Language Models
With Apple Intelligence, we're integrating powerful generative AI right into the apps and experiences people use every day, all while…
On-Device LLM Leaderboard
Intelligence × decode speed × memory × quantization retention, under real iPhone limits. Same protocol for every model; Apple's built-in FM on the board.
Introducing On device AI capabilities inside the Craft Assistant
A first look at the future of on-device AI models integrated into productivity tools
Optimizing On-Device Inference for Apple Silicon
A custom local engine that improves prefill and decode throughput
