🔍 Results for "local llm"

News

Someone Just Ran a 400 Billion Parameter AI Model on an iPhone 17 Pro — And the Real Story Is More Nuanced Than the Headlines Suggest

A developer ran a 400 billion parameter AI model on an iPhone 17 Pro at 0.6 tokens per second. The headline is impressive but the real story is more nuanced.

Mar 24, 2026 · 7 min read

Tutorials

A Guy Built a Custom C Engine That Runs a 397 Billion Parameter AI Model on a Regular MacBook — Here Is How Flash-Moe Actually Works

Flash-Moe is a pure C/Metal inference engine that runs Qwen3.5-397B on a MacBook Pro with 48GB RAM at 4.4 tokens per second by streaming expert weights from SSD. No Python, no frameworks — just raw performance.

Mar 22, 2026 · 7 min read

AI Tools

CanIRun.ai Finally Answers the Question Every Local AI Enthusiast Has Been Googling for Two Years

CanIRun.ai is a free web tool that maps AI model hardware requirements against your machine specs. With 762 upvotes on Hacker News, it covers everything from 0.5 GB edge models to 512 GB monsters.

Mar 13, 2026 · 6 min read