Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Victor M Profile picture
@victormustar
May 19 • 5 tweets • 2 min read • Read on X
Mac owners don't miss this: MLX LM is now integrated directly within Hugging Face 🤯

⬇️ Run 4,400+ LLMs locally on Apple Silicon at max speed, no cloud, no wait.
You need to toggle MLX LM in your local apps settings:
huggingface.co/settings/local…Image
Then browse compatible models here:
huggingface.co/models?library…
Bonus: snippet to launch an OpenAI SDK-compatible server is here too. Image
Huge thanks to the (super active) mlx-lm contributors 🚀 - Hope this feature helps this awesome library grow even more:github.com/ml-explore/mlx…

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Victor M

Victor M Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @victormustar

Victor M Profile picture
Mar 7
QwQ-32B changed local AI coding forever 🤯

We now have SOTA performance at home. Sharing my stack + tips ⬇️
All tools we are going to use are free, open source, and cross-platform (Windows/Mac/Linux): LM Studio, Aider and Hugging Face.
First thing first: QwQ-32B is an architect model, not an editor model, which makes all the difference for AI coding. ()aider.chat/2024/12/03/qwq…
Read 8 tweets
Victor M Profile picture
Feb 17
Forget GPT wrappers: 2025 is the year of hyper-specialized small reasoning models.

Someone made a UI reasoning model, it's a SFT fine-tuning of Qwen-7B trained on 500 samples. For landing page generation results are already on par with most closed models (it's a 7B...)

⬇️ model & dataset availableImage
model: huggingface.co/smirki/UIGEN-T…
dataset: huggingface.co/datasets/smirk…
Read 5 tweets
Victor M Profile picture
Mar 19, 2023
I just made my own Star Wars clip using AI (text-to-video)!
Here is how to do it yourself (it took me about 10 minutes from start to finish).

First, to work faster and more comfortably (and with zero waiting/queue time), I duplicated the original HF Space.


huggingface.co/spaces/damo-vi…
I changed the hardware to A10G large in the Space settings. Don't forget to set a sleep time so you don't pay while you're not using it.


It takes less than 20 sec to create a new video! If you use it for ~30 minutes it will generate a lot of clips and cost you ~$1.5!
Read 5 tweets
Victor M Profile picture
Mar 15, 2023
✨ Introducing Paper Pages on the Hugging Face Hub ✨
👀 Take a look at the T5 Paper Page: huggingface.co/papers/1910.10…
📌 You can access Paper Pages from models & datasets pages. Clicking on the Paper tag then "View paper page":
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(