Tag feed

#mlx

17 posts0 followers

Explore Hashnode

Alternatives

Trending tags this week

Ssatyasutarprimitives.hashnode.devJun 13 · 11 min read

Building an Enterprise Second Brain Locally with MLX + OpenCode

What Is an Enterprise Second Brain? The term "second brain" was popularized by productivity thinkers as a way to describe an external system for capturing, organizing, and retrieving knowledge — freei

0

RCRobert Collinsselfenrichment.hashnode.devJun 3 · 8 min read

BF16 Edge Cases When Porting CUDA-Oriented TTS Models to MPS and MLX-Audio

When porting CUDA-oriented TTS models to Apple Silicon, one subtle but important issue is BF16 behavior on Metal. This has shown up in DiaTTS work on MPS, and the same class of issue appears relevant

0

RCRobert Collinsselfenrichment.hashnode.devMay 11 · 16 min read

Revisiting MetalGraph: What I Learned About MLX, Replay, and Sidecar Performance

To set the stage, this post covers follow-up work that made MetalGraph feel less like it is doomed to be only a pure investigation tool and more like something that could be useful in practice. MetalG

0

RCRobert Collinsselfenrichment.hashnode.devMay 10 · 14 min read

The Honest Limits Reached With MetalGraph

Metal Graph is an early-stage reusable explicit graph execution API over Apple Metal. MetalGraph started with a simple question: can I (or rather, chatGPT and I) build something graph-like around Appl

0

SNSaloni Narangkubesimplify.hashnode.devApr 30 · 10 min read

Day 6: Run an LLM on Your Laptop - With Docker

7 Days of Docker (2026) - A Docker Captain's guide. Not your average tutorial. I'm a Docker Captain. And if you'd told me two years ago that I'd be pulling AI models from Docker Hub the same way I pu

1

E

SSleepyQuantsleepyquant.hashnode.devApr 23 · 8 min read

I Run a 40GB AI Model on a MacBook. Three Months of MLX on M1 Max Has Changed How I Think About Apple Silicon.

I Run a 40GB AI Model on a MacBook. Three Months of MLX on M1 Max Has Changed How I Think About Apple Silicon. It's Just a Laptop. But It's Running a 40GB Model Right Now. I'm drafting this on a MacBook Pro. Qwen 3.6 35B-A3B MoE Q8 — about 40GB of we...

0

MMMatt Macoskoineedhemp.hashnode.devApr 23 · 5 min read

Free AI on a MacBook vs $100-a-Month Claude Code — Hexagon Shootout

▶ Watch the race on YouTube: https://www.youtube.com/watch?v=2KeTDDodE0A April 22, 2026. Anthropic's Claude Code Max plan jumped to $100 a month. I ran a live three-way AI race on the exact same prompt — Gemma 31B local, Llama 70B local, and Claude...

0

AWAlan Westalan-west.hashnode.devApr 6 · 5 min read

Ollama Just Got 93% Faster on Mac. Here's How to Enable It.

My M4 Max was decoding Qwen3.5 at 58 tokens per second yesterday. Today it's doing 112. Same model, same hardware, same prompt. The only thing that changed was a single environment variable. Ollama 0.19 shipped on March 31, 2026 with a preview of its...

0

FEFazm Engineeringfazm.hashnode.devMar 18 · 3 min read

On-Device AI on Apple Silicon - What It Means for Desktop Agents

Apple Silicon changed what is possible for local AI. The unified memory architecture means ML models can run on the GPU without copying data between CPU and GPU memory. For a desktop agent that needs to process screen content in real-time, this matte...

0

AJAKSHAY JADHAVakshayjadhav.hashnode.devMar 14 · 8 min read

I Tried Running FunctionGemma On-Device in a React Native App. Here's How It Went.

It started with a tweet. Google Devs posted a demo of FunctionGemma running a game, and I watched this tiny model parse natural language into structured function calls in real time. My immediate thoug

0

#mlx

Search Hashnode

#mlx

Explore Hashnode

Trending tags this week

Building an Enterprise Second Brain Locally with MLX + OpenCode

BF16 Edge Cases When Porting CUDA-Oriented TTS Models to MPS and MLX-Audio

Revisiting MetalGraph: What I Learned About MLX, Replay, and Sidecar Performance

The Honest Limits Reached With MetalGraph

Day 6: Run an LLM on Your Laptop - With Docker

I Run a 40GB AI Model on a MacBook. Three Months of MLX on M1 Max Has Changed How I Think About Apple Silicon.

Free AI on a MacBook vs $100-a-Month Claude Code — Hexagon Shootout

Ollama Just Got 93% Faster on Mac. Here's How to Enable It.

On-Device AI on Apple Silicon - What It Means for Desktop Agents

I Tried Running FunctionGemma On-Device in a React Native App. Here's How It Went.