GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com โ€” IonDen - Overview

@IonDen IonDen Follow
More
  • Overview
  • Repositories
  • Projects
  • Packages
  • Stars
@IonDen
IonDen
Follow
View IonDen's full-sized avatar

Denis Ineshin IonDen

Follow
Sponsor
Senior Full Stack Engineer @ Booking.com
255 followers ยท 22 following
  • Booking.com
  • Amsterdam, Netherlands
  • https://ineshin.space

Achievements

Achievement: YOLOAchievement: Pull Sharkx3Achievement: QuickdrawAchievement: Galaxy BrainAchievement: Arctic Code Vault ContributorAchievement: Starstruckx3

Achievements

Achievement: YOLOAchievement: Pull Sharkx3Achievement: QuickdrawAchievement: Galaxy BrainAchievement: Arctic Code Vault ContributorAchievement: Starstruckx3
More
  • Overview
  • Repositories
  • Projects
  • Packages
  • Stars
IonDen/README.md

Open source libraries for MLX and Apple Silicon

Hi, I'm Denis ๐Ÿ‘‹

I write open source libraries for MLX, Apple's machine learning framework for Apple Silicon. I'd like my Mac to run and inspect real models without renting a GPU in some datacenter, so I build the small tools that make that possible and put them on PyPI.

Most of them do unglamorous things. One previews an image while it is still generating instead of making you wait for the final pixels. One lets FLUX skip work it has already done. One checks a model repo for problems before they take your load down with them. One measures what quantization quietly costs you in quality. Niche stuff, all of it. These were just the walls I kept walking into.

Every one started as a script I got tired of copy-pasting between projects. That is usually how it goes.

If any of it saves you an afternoon:

  • โ˜• Buy me a coffee
  • ๐Ÿค Sponsor my work
  • ๐Ÿ”ญ Follow along

Pinned Loading

  1. mlx-taef mlx-taef Public

    Tiny AutoEncoders (TAESD family) for diffusion latents on Apple Silicon โ€” pure MLX. Live previews + low-memory decode for FLUX.1, FLUX.2 Klein, SD1.x, SDXL.

    Python 13 3

  2. mlx-teacache mlx-teacache Public

    TeaCache step-skipping for FLUX, Qwen-Image & Z-Image diffusion on Apple Silicon, in pure MLX

    Python 7 1

  3. mlx-model-doctor mlx-model-doctor Public

    Validate an MLX / Hugging Face model repository before you load it.

    Python 6 2

  4. mlx-train-perf mlx-train-perf Public

    Fused, logit-free linear-cross-entropy loss, RAM-fit planner, and benchmark harness for MLX fine-tuning on Apple Silicon

    Python 6 1

  5. mlx-quant-fidelity mlx-quant-fidelity Public

    Measure quantization quality loss on Apple Silicon MLX โ€” KL divergence, top-token flip rate and perplexity delta for KV-cache and weight quantization

    Python 4 1

  6. mlx-guard mlx-guard Public

    External runtime safety supervision for MLX workloads on Apple Silicon

    Rust 4 1

Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.

Uh oh!

There was an error while loading. Please reload this page.

You are visitor 01402503 โ€” GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800ร—600. No cookies required.