Loading video...

Video Failed to Load

Go Home

DiffusionKit now supports Stable Diffusion 3 Medium MLX Python and Core ML Swift Inference work great for on-device inference on Mac! MLX: Core ML: Mac App: Hugging Face Diffusers App (Pending App Store review)

argmax's profile picture

argmax

4,491 subscribers

73,996 views • 2 years ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

7 Comments

John Coin's profile picture
John Coin2 years ago

@huggingface Would it be possible to make a ComfyUI node from this ?

UserInterface's profile picture
UserInterface3 years ago

How to Detect an Apple AirTag Tracker Without an Apple Device

Justin Trugman's profile picture
Justin Trugman2 years ago

@huggingface It's working awesome! Check out this Clone Trooper I generated on my M3 Pro Macbook Pro

marcelo Sanchez's profile picture
marcelo Sanchez2 years ago

@huggingface no ANE usage?

argmax's profile picture
argmax2 years ago

@huggingface This is the initial support. ANE inference via Core ML and compressed models will be included in a future release.

Jason Stock's profile picture
Jason Stock2 years ago

@huggingface Stoked to try the app and love the transparency with the sampling step previews. Any way to change the solver, noise schedule, etc?

Dylan White's profile picture
Dylan White1 year ago

@huggingface Very cool. Id love to try it.

Related Videos

Stray is now available on macOS through the Mac App Store and Steam. Mac App Store: Steam:
1:29

Stray is now available on macOS through the Mac App Store and Steam. Mac App Store: Steam:

Annapurna Interactive

49,745 views • 2 years ago

Your Mac is about to run inference like a datacenter. Coming soon to MLX-Swift: Continuous batching: the fastest way to handle multiple inference streams locally. It starts with regular inference and seamlessly upgrades to batched mode when new requests arrive. The best of both worlds. Based on the work of and Awni Hannun
0:25

Your Mac is about to run inference like a datacenter. Coming soon to MLX-Swift: Continuous batching: the fastest way to handle multiple inference streams locally. It starts with regular inference and seamlessly upgrades to batched mode when new requests arrive. The best of both worlds. Based on the work of and Awni Hannun

Ronald Mannak

60,570 views • 7 months ago

Offline vibe coding with Gemma 4. This open-source Electron app runs entirely on your Mac via Apple's MLX framework. No Wi-Fi required.
0:43

Offline vibe coding with Gemma 4. This open-source Electron app runs entirely on your Mac via Apple's MLX framework. No Wi-Fi required.

Google Gemma

387,372 views • 1 month ago

As part of our goal to make MLX a great research tool, we're expanding support to new languages like Swift and C, making experimentation on Apple silicon easier for ML researchers. Video generating text with Mistral 7B and MLX Swift 👇 MLX is an array framework for machine learning research on Apple silicon. MLX is intended for research and not for production deployment of models in apps.
0:56

As part of our goal to make MLX a great research tool, we're expanding support to new languages like Swift and C, making experimentation on Apple silicon easier for ML researchers. Video generating text with Mistral 7B and MLX Swift 👇 MLX is an array framework for machine learning research on Apple silicon. MLX is intended for research and not for production deployment of models in apps.

Awni Hannun

88,726 views • 2 years ago

⌘ + ⇧ + M Our new voice mode is now on the Perplexity macOS app. Download or update the app from the Mac App Store.
0:28

⌘ + ⇧ + M Our new voice mode is now on the Perplexity macOS app. Download or update the app from the Mac App Store.

Perplexity

63,254 views • 1 year ago

Dookey Dash: Unclogged has been un-puckered and is ready for entry. Download the game now on the: App Store: Google Play Store: Mac: PC:
0:29

Dookey Dash: Unclogged has been un-puckered and is ready for entry. Download the game now on the: App Store: Google Play Store: Mac: PC:

Bored Ape Yacht Club 🍌

271,538 views • 1 year ago

Run Qwen-TTS on Your Mac, natively. Blaine Brown has created Qwen3-TTS MLX WebUI Enhanced, a Web UI for running Qwen-TTS using the Mac-native MLX framework, powered by MLX-Audio from Prince Canuma, it runs very smooth! 1-click install on pinokio (Apple Silicon Macs)
0:40

Run Qwen-TTS on Your Mac, natively. Blaine Brown has created Qwen3-TTS MLX WebUI Enhanced, a Web UI for running Qwen-TTS using the Mac-native MLX framework, powered by MLX-Audio from Prince Canuma, it runs very smooth! 1-click install on pinokio (Apple Silicon Macs)

cocktail peanut

168,965 views • 3 months ago

Gemma3n + MLX 🚀 Run DeepMind's first open-source Omni Model on Your Mac! Get started: > pip install -U mlx-vlm
3:24

Gemma3n + MLX 🚀 Run DeepMind's first open-source Omni Model on Your Mac! Get started: > pip install -U mlx-vlm

Prince Canuma

31,873 views • 11 months ago

Update: Qwen3.5:9b head-to-head (MLX, Apple Silicon optimized) Mac Studio M2 Ultra: 89.74 tok/s Mac Mini M4: 20.82 tok/s MLX basically doubles the speed on both machines.
1:02

Update: Qwen3.5:9b head-to-head (MLX, Apple Silicon optimized) Mac Studio M2 Ultra: 89.74 tok/s Mac Mini M4: 20.82 tok/s MLX basically doubles the speed on both machines.

stevibe

134,256 views • 3 months ago

Neva: Prologue launches tomorrow! Get emotional on Nintendo Switch, Steam, Xbox Series, PS4, PS5, and Mac App Store for $2.99.
1:02

Neva: Prologue launches tomorrow! Get emotional on Nintendo Switch, Steam, Xbox Series, PS4, PS5, and Mac App Store for $2.99.

Devolver Digital

35,821 views • 3 months ago

Semi-realtime Stable Diffusion image-to-image (Van Gogh style), Unity plugin based on Apple's Core ML port. The latency is about 2 seconds on M1 Max MacBook Pro.
1:05

Semi-realtime Stable Diffusion image-to-image (Van Gogh style), Unity plugin based on Apple's Core ML port. The latency is about 2 seconds on M1 Max MacBook Pro.

Keijiro Takahashi

291,867 views • 3 years ago

Sam-Audio by AI at Meta is now on MLX-Audio 🔊 You can now isolate voices or sounds from any audio locally in your Mac. I added this simple UI to the MLX-Audio studio app to help you get started Note: - The release is coming soon for now please install from source. - Vision part was excluded for now. Let me know if you need it. - PR for UI:
1:38

Sam-Audio by AI at Meta is now on MLX-Audio 🔊 You can now isolate voices or sounds from any audio locally in your Mac. I added this simple UI to the MLX-Audio studio app to help you get started Note: - The release is coming soon for now please install from source. - Vision part was excluded for now. Let me know if you need it. - PR for UI:

Prince Canuma

19,027 views • 5 months ago

You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.
1:04

You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.

OpenAI

4,718,848 views • 21 days ago

🚀 WeatherWise Plus for Desktop: Introducing Our Mac & Windows App Today we're launching our dedicated desktop app, exclusively for WeatherWise Plus users. Simply subscribe to WeatherWise Plus on your iOS or Android device, link your subscription with a WeatherWise Account, and enjoy premium weather features right on your desktop. Download for Mac: Download for Windows: Our browser app is still free and available at
0:39

🚀 WeatherWise Plus for Desktop: Introducing Our Mac & Windows App Today we're launching our dedicated desktop app, exclusively for WeatherWise Plus users. Simply subscribe to WeatherWise Plus on your iOS or Android device, link your subscription with a WeatherWise Account, and enjoy premium weather features right on your desktop. Download for Mac: Download for Windows: Our browser app is still free and available at

WeatherWise.app

16,295 views • 1 year ago

Introducing Rork Companion Mac app Until now, if you wanted to build  apps with Swift, you had to install 30GB of Xcode, struggle with certificates, TestFlight, and pay $120 to test on your iPhone Rork Companion solves all of it with a Mac app that can install up to 3 iOS apps on your phone, no $99 Apple Developer account needed P.S. You still need an Apple Developer account to publish to the App Store
0:50

Introducing Rork Companion Mac app Until now, if you wanted to build  apps with Swift, you had to install 30GB of Xcode, struggle with certificates, TestFlight, and pay $120 to test on your iPhone Rork Companion solves all of it with a Mac app that can install up to 3 iOS apps on your phone, no $99 Apple Developer account needed P.S. You still need an Apple Developer account to publish to the App Store

Rork

239,811 views • 3 months ago

oMLX is working really well as single machine inference engine for coding agents! Caching is managed perfectly (it can use a ton of disk space, be aware!) and oQ quantization delivers great results. Behind the scenes it uses the standard MLX building blocks (75% created by Prince Canuma 🙏): - mlx-lm - mlx-vlm - mlx-embeddings - mlx-audio I tested Qwen3.6-35B-A3B-oQ6 on M5 Max with two pi instances and it was fast and furious and leveraging cache like crazy as you can see in the video. Let me try to create some oQ versions (2,4,6?) of MiniMax M2.7 now and then I'll pass to distributed inference. I must win! 💪
3:57

oMLX is working really well as single machine inference engine for coding agents! Caching is managed perfectly (it can use a ton of disk space, be aware!) and oQ quantization delivers great results. Behind the scenes it uses the standard MLX building blocks (75% created by Prince Canuma 🙏): - mlx-lm - mlx-vlm - mlx-embeddings - mlx-audio I tested Qwen3.6-35B-A3B-oQ6 on M5 Max with two pi instances and it was fast and furious and leveraging cache like crazy as you can see in the video. Let me try to create some oQ versions (2,4,6?) of MiniMax M2.7 now and then I'll pass to distributed inference. I must win! 💪

Ivan Fioravanti ᯅ

19,258 views • 1 month ago

This is the best Open Source TTS available on Mac right now. Watch Peter break it down. I combined two Qwen3-TTS projects. One for MLX speed & the other for its beautiful UI (but was slow on Mac). Then added a bunch of features. Qwen3-TTS-MLX-WebUI-Enhanced Install via Pinokio
2:27

This is the best Open Source TTS available on Mac right now. Watch Peter break it down. I combined two Qwen3-TTS projects. One for MLX speed & the other for its beautiful UI (but was slow on Mac). Then added a bunch of features. Qwen3-TTS-MLX-WebUI-Enhanced Install via Pinokio

Blaine Brown

167,095 views • 3 months ago