Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI
See more: https://x.com/adrgrondin/status/20405... Speaker info: https://x.com/adrgrondin
▶︎
I Turned My iPhone Into an AI Productivity Machine.
▶︎
$10,000 Mac Studio vs. $10 AI Agent
▶︎
Google AI Edge Gallery Tutorial - How To Run LLMS Locally On Your Phone
▶︎
Your local LLM is 10x slower than it should be
▶︎
Run MLX LLMs 23% Faster on a Mac with MTP
▶︎
My M5 Max, Gemma 4, MLX LOCAL Stack. (This KILLS MODEL PROVIDERS)
▶︎
Apple MLX vs llama.cpp: Which is Really Faster? (4 Runtimes - Ollama Included)
▶︎
This Shouldn’t Be Able to Run 120B Locally
▶︎
Anthropic Workshop: Build Agents That Run for Hours — Ash Prabaker & Andrew Wilson
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
▶︎
Yann LeCun's $1B Bet Against LLMs [Part 1]
▶︎
Ollama Just Got 2x Faster on Mac (Here's How)
▶︎
Harnesses in AI: A Deep Dive — Tejas Kumar, IBM
▶︎
Fine Tune a model with MLX for Ollama
▶︎
Master Gemma 4 in 20 Minutes
▶︎
you need to use Hermes RIGHT NOW!! (goodbye OpenClaw!!)
▶︎
Full Walkthrough: Workflow for AI Coding — Matt Pocock
▶︎
China Is About To Pop The AI Bubble
▶︎
Private AI on the go… a new trick
▶︎
I Tested Gemma 4 vs Gemini 3.1 So You Don't Have To
▶︎