Mirai Blog
Company updates, educational articles and researches
Mar 31, 2026
LFM2.5-350M on Apple Silicon
Mar 30, 2026
Why activation quantization is harder than weight quantization (and what to do about it).
Mar 24, 2026
How to improve acceptance rate in speculative decoding?
Mar 23, 2026
Exploring Metal Performance Primitives on any M-series chip
Feb 19, 2026
Mirai raises $10M to build the on-device AI capability layer.
Apr 3, 2025
Mirai iOS SDK Public Preview
Mar 24, 2025
Part 4: Brief history of Apple ML Stack
Part 3: iPhone Hardware and How It Powers On-Device AI
Mar 23, 2025
Part 2: How to Understand On-Device AI
Mar 22, 2025
Part 1: Introduction to Deploying LLMs on Mobile
Talk to us
Product
Models library
MacOS app
Docs
Company
Main
Links
Platform / SDK
Inference Runtime
Models Conversion
Models Library
MacOS App
Blog
About us
Careers
Contact Us
Privacy Policy
Terms of Use
X (Twitter)
Github
LinkedIn
Discord