Adrien Grondin's banner
Adrien Grondin's profile picture

Adrien Grondin

@adrgrondin • 8,527 subscribers

Apple Platforms @lmstudio building @LocallyAIApp

Shorts

The iPhone 18 Pro is much better than what I expected for on-device AI It can run a 27B model at double the speed of the 17 Pro The new A20 Pro chip is a beast

The iPhone 18 Pro is much better than what I expected for on-device AI It can run a 27B model at double the speed of the 17 Pro The new A20 Pro chip is a beast

427,065 views

With iOS 27 Apple introduced its most powerful on-device model: AFM 3 Core Advanced It’s a 20 billion parameters model activating only between 1 to 4 billion parameters depending on the request Here’s the model running on iPhone 17 Pro

With iOS 27 Apple introduced its most powerful on-device model: AFM 3 Core Advanced It’s a 20 billion parameters model activating only between 1 to 4 billion parameters depending on the request Here’s the model running on iPhone 17 Pro

472,311 views

Google’s Gemma 4 E2B running on-device on iPhone 17 Pro Gemma 4 is built from the same research as Gemini 3, has image understanding capabilities and can reason if needed Running at ~40tk/s with MLX optimized for Apple Silicon

Google’s Gemma 4 E2B running on-device on iPhone 17 Pro Gemma 4 is built from the same research as Gemini 3, has image understanding capabilities and can reason if needed Running at ~40tk/s with MLX optimized for Apple Silicon

1,045,843 views

Here’s Apple’s foundation model running on iPhone 17 Pro It’s just so fast Apple was not joking, the A19 Pro chip is really good for running LLMs on-device

Here’s Apple’s foundation model running on iPhone 17 Pro It’s just so fast Apple was not joking, the A19 Pro chip is really good for running LLMs on-device

1,566,067 views

Side by side comparison of Apple’s on-device foundation model iPhone 16 Pro vs 17 Pro ~55 tk/s for the 16 Pro and ~85 tk/s for the 17 Pro

Side by side comparison of Apple’s on-device foundation model iPhone 16 Pro vs 17 Pro ~55 tk/s for the 16 Pro and ~85 tk/s for the 17 Pro

907,443 views

Google's Gemma 4 26B A4B running on MacBook Pro M5 Max 100% native Swift Achieving over 100tk/s with Apple MLX framework

Google's Gemma 4 26B A4B running on MacBook Pro M5 Max 100% native Swift Achieving over 100tk/s with Apple MLX framework

351,153 views

Another demo of Apple 20B on-device foundation model that comes with iOS 27 The new models support image understanding (on all iPhone with the new OS) Very good at OCR

Another demo of Apple 20B on-device foundation model that comes with iOS 27 The new models support image understanding (on all iPhone with the new OS) Very good at OCR

58,553 views

Apple wasn’t kidding, the iPhone 17 Pro is really built for running LLMs Here’s LFM2 8B A1B by running on-device with MLX in Locally AI - Local AI Chat, the iPhone runs the 8B model with zero struggle Thanks Prince Canuma for the port to MLX, it made the MLX Swift port possible

Apple wasn’t kidding, the iPhone 17 Pro is really built for running LLMs Here’s LFM2 8B A1B by running on-device with MLX in Locally AI - Local AI Chat, the iPhone runs the 8B model with zero struggle Thanks Prince Canuma for the port to MLX, it made the MLX Swift port possible

493,561 views

Demo of 1-bit Bonsai 8B from PrismML running on-device on iPhone 17 Pro More than 40tk/s for a dense 8B model on iPhone, that’s a first Powered by Apple MLX and available now in Locally AI

Demo of 1-bit Bonsai 8B from PrismML running on-device on iPhone 17 Pro More than 40tk/s for a dense 8B model on iPhone, that’s a first Powered by Apple MLX and available now in Locally AI

161,153 views

New side panel in Locally. Conversations are now easier to access and search. Also more Liquid Glass!

New side panel in Locally. Conversations are now easier to access and search. Also more Liquid Glass!

93,606 views

The new PrismML’s Bonsai 27B model running on iPhone 17 Pro Bonsai 27B is the first 27B-class model to run on a phone and it uses less than 5GB of memory Pushing the limits on what can run a phone

The new PrismML’s Bonsai 27B model running on iPhone 17 Pro Bonsai 27B is the first 27B-class model to run on a phone and it uses less than 5GB of memory Pushing the limits on what can run a phone

67,095 views

WIP Thinking UI for Qwen 3 thinking mode, running locally on iPhone. Tried to have something similar to Grok web thinking UI. Made 100% with SwiftUI.

WIP Thinking UI for Qwen 3 thinking mode, running locally on iPhone. Tried to have something similar to Grok web thinking UI. Made 100% with SwiftUI.

64,271 views

I wanted to try Maple-Preview by DeepGrove on iPhone so I simply ported the model to MLX Swift using Bionic Maple runs at ~80tk/s on iPhone 17 Pro with my quick port, it’s a 20B-A1B model at 2-bit The model is close to Qwen3.5 35-A2B in many benchs and runs easily on iPhone

I wanted to try Maple-Preview by DeepGrove on iPhone so I simply ported the model to MLX Swift using Bionic Maple runs at ~80tk/s on iPhone 17 Pro with my quick port, it’s a 20B-A1B model at 2-bit The model is close to Qwen3.5 35-A2B in many benchs and runs easily on iPhone

13,376 views

Quick demo of LFM 2.5 VL 1.6B model by Liquid AI that I recently added to Locally AI - Local AI Chat Running locally on iPhone 17 Pro at ~90tk/s with MLX Small vision-language models are improving fast

Quick demo of LFM 2.5 VL 1.6B model by Liquid AI that I recently added to Locally AI - Local AI Chat Running locally on iPhone 17 Pro at ~90tk/s with MLX Small vision-language models are improving fast

32,556 views

We made it easy to run local models on your computer and use them from your phone. A secure, end-to-end encrypted connection in just a few clicks. Available now with LM Studio and Locally AI - Local AI Chat.

We made it easy to run local models on your computer and use them from your phone. A secure, end-to-end encrypted connection in just a few clicks. Available now with LM Studio and Locally AI - Local AI Chat.

12,045 views

Really impressed by quality of Marvis-AI made by Prince Canuma & Lucas Newman, it's only 250M and uses less than 500MB in 4-bit 🤯 You only need 2 lines of code to run on macOS: pip install -U mlx-audio python -m mlx_audio.tts.generate --model Marvis-AI/marvis-tts-250m-v0.1 --stream \ --text "Hello there!" No reason not to give it a try!

Really impressed by quality of Marvis-AI made by Prince Canuma & Lucas Newman, it's only 250M and uses less than 500MB in 4-bit 🤯 You only need 2 lines of code to run on macOS: pip install -U mlx-audio python -m mlx_audio.tts.generate --model Marvis-AI/marvis-tts-250m-v0.1 --stream \ --text "Hello there!" No reason not to give it a try!

11,780 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

The new Qwen 3.5 by Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon.
0:25
adrgrondin's profile picture

The new Qwen 3.5 by Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon.

Adrien Grondin

3,561,865 views • 7 months ago

Qwen 3.8 27B doing an agentic task with subagent at ~120 tok/s on M5 Max MacBook Pro in LM Studio Bionic using Inco AI Splash engine At launch a little more than a month ago the model was running around ~20tk/s It’s 6x faster now, local AI is progressing at lightning speed!
0:45
adrgrondin's profile picture

Qwen 3.8 27B doing an agentic task with subagent at ~120 tok/s on M5 Max MacBook Pro in LM Studio Bionic using Inco AI Splash engine At launch a little more than a month ago the model was running around ~20tk/s It’s 6x faster now, local AI is progressing at lightning speed!

Adrien Grondin

47,846 views • 26 days ago

The new Qwen 3.5 4B runs incredibly well on M5. The model is close to GPT-4o in benchmarks. Running fully on-device with MLX.
0:20
adrgrondin's profile picture

The new Qwen 3.5 4B runs incredibly well on M5. The model is close to GPT-4o in benchmarks. Running fully on-device with MLX.

Adrien Grondin

230,466 views • 7 months ago

Subagents running locally and simultaneously on MacBook Pro M5 with Codex CLI + LM Studio to review code and find bugs using Qwen 3.6 Powered by the updated MLX engine with batching in beta in the app The batching speed boost is noticeable
1:40
adrgrondin's profile picture

Subagents running locally and simultaneously on MacBook Pro M5 with Codex CLI + LM Studio to review code and find bugs using Qwen 3.6 Powered by the updated MLX engine with batching in beta in the app The batching speed boost is noticeable

Adrien Grondin

75,549 views • 5 months ago

I’ve been using the new MacBook Pro M5 since launch and it’s a beast, especially compared to my old M1! It’s good for running the smaller AI models locally but also everything you do is just so fast. Here’s Gemma 3 QAT 12B running with MLX:
0:35
adrgrondin's profile picture

I’ve been using the new MacBook Pro M5 since launch and it’s a beast, especially compared to my old M1! It’s good for running the smaller AI models locally but also everything you do is just so fast. Here’s Gemma 3 QAT 12B running with MLX:

Adrien Grondin

101,950 views • 10 months ago

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks
0:21
adrgrondin's profile picture

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

Adrien Grondin

109,700 views • 1 year ago

Early WIP port of Gemma 4 multi-token prediction (MTP) on MLX Swift With MTP, Gemma 31B is 30-40% faster on M5 Max and with zero quality degradation A significant speedup by just adding a 900MB MTP drafter model
0:20
adrgrondin's profile picture

Early WIP port of Gemma 4 multi-token prediction (MTP) on MLX Swift With MTP, Gemma 31B is 30-40% faster on M5 Max and with zero quality degradation A significant speedup by just adding a 900MB MTP drafter model

Adrien Grondin

35,875 views • 5 months ago

I gave SmolLM3 by Hugging Face a voice 🗣️ Here’s a demo of me talking with the model hands-free on iPhone, thanks to built-in voice activity detection Everything runs fully on-device, powered by Apple MLX
1:45
adrgrondin's profile picture

I gave SmolLM3 by Hugging Face a voice 🗣️ Here’s a demo of me talking with the model hands-free on iPhone, thanks to built-in voice activity detection Everything runs fully on-device, powered by Apple MLX

Adrien Grondin

56,493 views • 1 year ago

Translating a full-length news article on iPhone 17 Pro with TranslateGemma from Google DeepMind The model works incredibly well on long text Running fully on-device with MLX
0:46
adrgrondin's profile picture

Translating a full-length news article on iPhone 17 Pro with TranslateGemma from Google DeepMind The model works incredibly well on long text Running fully on-device with MLX

Adrien Grondin

15,493 views • 8 months ago

No more content to load