Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

MLX: Tom Riddle's diary running locally on an iPad powered by Apple MLX with Gemma 4 E4B behind the scene. Children can go crazy for something like this, no? 🔥

Ivan Fioravanti ᯅ

42,599 subscribers

32,359 Aufrufe • vor 2 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

23 Kommentare

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 2 Monaten

I'll need your help in setting up some guardrails before creating damage 🤣

Profilbild von Hugo Pinheiro

Hugo Pinheirovor 2 Monaten

Can be taken further ie: in the book diamond age they have "A Young Lady's Illustrated Primer" which is similar but much more like a reactive wiki with stories that help kids learn.

Profilbild von Ömer Çelik

Ömer Çelikvor 2 Monaten

We need this ASAP before our next flight!

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 2 Monaten

You know how to build it now 😉

Profilbild von Piotr Kosecki

Piotr Koseckivor 2 Monaten

With local model I was able to create a chrome plugin which changes certain news pages into newspapers like from Harry Potter - with moving images:

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 2 Monaten

WOW COOL!

Profilbild von Eugene Pyvovarov

Eugene Pyvovarovvor 2 Monaten

you have to release this, but also make it to connect to chatgpt/grok maybe, not all iPads can run gemma or at least source code ;)

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 2 Monaten

Can't add copyrighted material. Need to invent something here...

Profilbild von danilo

danilovor 2 Monaten

honestly this could be a top10 app in app store between a month

Profilbild von Angel

Angelvor 2 Monaten

beautiful

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 2 Monaten

🙏

Profilbild von Mariusz Kurman

Mariusz Kurmanvor 1 Monat

Cool man 😆

Profilbild von Eduardo Bettio✍️🎭®

Eduardo Bettio✍️🎭®vor 1 Monat

Me dejaste impresionado ! Muy buena idea ! Y con gemma4 !!!!!!! Las limitaciones se difuminan segundo a segundo!

Profilbild von Celestial Rose

Celestial Rosevor 2 Monaten

Oh wow I love it so much

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 2 Monaten

Thanks 🙏 This gave me so many ideas!!! 🚀 But guardrails are vital.

Profilbild von Celestial Rose

Celestial Rosevor 2 Monaten

If you deploy it make sure to remove any copyright material ! You could add nice transitions animations to when text is showing up, with traces and some masks; that would add it to the magic effect

Profilbild von Ivan Fioravanti ᯅ

Ivan Fioravanti ᯅvor 2 Monaten

I can't deploy this, but I can create something completely new...

Profilbild von B (the mouth)

B (the mouth)vor 2 Monaten

Love it!! I made my AI to do my medical reports from voice, super efficient but this is much more fun

Profilbild von Eden Gilbert

Eden Gilbertvor 1 Monat

Opensource it :)

Profilbild von Marcel Huber

Marcel Hubervor 2 Monaten

Someone trained this with his own handwriting looks even cooler

Profilbild von Tom Bielecki

Tom Bieleckivor 2 Monaten

You're gonna be so rich off this

Profilbild von Michael Tierney

Michael Tierneyvor 2 Monaten

@awnihannun The real question is what does Apple actually do with Gemini, not how much they pay for it.

Profilbild von Mockapapella

Mockapapellavor 2 Monaten

If you implement something like this you can show where every connected device is on your network: Just an example of WiFi based geolocation, there are a lot of other similar papers going back at least 6 years or so

Ähnliche Videos

A perfect coding model for MLX on Apple silicon.. Qwen delivered again. Runs quite fast on an M3 Ultra. Running the 4-bit quantized with mlx-lm:

A perfect coding model for MLX on Apple silicon.. Qwen delivered again. Runs quite fast on an M3 Ultra. Running the 4-bit quantized with mlx-lm:

Awni Hannun

186,772 Aufrufe • vor 1 Jahr

Llama 3 running locally on iPhone with MLX Built by exo intern team Mohamed Baioumy h/t Awni Hannun MLX & Prince Canuma for the port

Llama 3 running locally on iPhone with MLX Built by exo intern team Mohamed Baioumy h/t Awni Hannun MLX & Prince Canuma for the port

Alex Cheema

295,873 Aufrufe • vor 2 Jahren

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)

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 Aufrufe • vor 7 Monaten

Hermes Agent Nous Research + Gemma 4 26B Google DeepMind, fully working on local Mac 🤯: one prompt → full CLI app + tests + pytest passing tool calls firing back to back — local Claude Code vibes Gemma 4 MoE is fast AND smart, and tool calling just works — powered by Rapid-MLX which natively parses Gemma 4's tool format (no other local backend can do this yet) Two lines to try it: pip install rapid-mlx & rapid-mlx serve gemma-4-26b pip install hermes-agent && hermes @teknaborat @siaborisov #HermesAgent #Gemma4 #LocalLLM

Hermes Agent Nous Research + Gemma 4 26B Google DeepMind, fully working on local Mac 🤯: one prompt → full CLI app + tests + pytest passing tool calls firing back to back — local Claude Code vibes Gemma 4 MoE is fast AND smart, and tool calling just works — powered by Rapid-MLX which natively parses Gemma 4's tool format (no other local backend can do this yet) Two lines to try it: pip install rapid-mlx & rapid-mlx serve gemma-4-26b pip install hermes-agent && hermes @teknaborat @siaborisov #HermesAgent #Gemma4 #LocalLLM

raullen

24,988 Aufrufe • vor 5 Monaten

Run the latest Ministral 3 models by Mistral AI on macOS. Running privately on-device and optimized for Apple Silicon with MLX.

Run the latest Ministral 3 models by Mistral AI on macOS. Running privately on-device and optimized for Apple Silicon with MLX.

Locally AI - Local AI Chat

34,901 Aufrufe • vor 9 Monaten

Next mlx-vlm release will ship with continuous batching support on the server 🚀 What's coming: → Continuous batching — new requests join the active batch immediately, no waiting. Mixed image + text batches supported → OpenAI-compatible API — field-for-field match with mlx-lm, reasoning/content split for thinking models, tag-aware streaming → Multi-turn tool calling — full tool use support across streaming and non-streaming, works with Gemma4 and other templates → Vision feature caching — cache image embeddings across turns. Gemma4: 228x speedup, Qwen3.5: 23x on cache hit All running locally on Apple Silicon. Check our this demo running 4 concurrent requests (mixed image + text) to gemma-4-26B-A4B-IT by Google Gemma in bf16 using Pi + MLX-VLM server on my M3 Ultra. One of the requests ingests a 8K resolution image!

Next mlx-vlm release will ship with continuous batching support on the server 🚀 What's coming: → Continuous batching — new requests join the active batch immediately, no waiting. Mixed image + text batches supported → OpenAI-compatible API — field-for-field match with mlx-lm, reasoning/content split for thinking models, tag-aware streaming → Multi-turn tool calling — full tool use support across streaming and non-streaming, works with Gemma4 and other templates → Vision feature caching — cache image embeddings across turns. Gemma4: 228x speedup, Qwen3.5: 23x on cache hit All running locally on Apple Silicon. Check our this demo running 4 concurrent requests (mixed image + text) to gemma-4-26B-A4B-IT by Google Gemma in bf16 using Pi + MLX-VLM server on my M3 Ultra. One of the requests ingests a 8K resolution image!

Prince Canuma

82,349 Aufrufe • vor 5 Monaten

Fast and local voice typing with Gemma 4. Phonon demonstrates the utility of lightweight, on-device models for privacy-preserving workflows. This open-source voice typing tool runs Gemma 4 (E2B 4-bit) locally via MLX to process audio and screen context without cloud routing.

Fast and local voice typing with Gemma 4. Phonon demonstrates the utility of lightweight, on-device models for privacy-preserving workflows. This open-source voice typing tool runs Gemma 4 (E2B 4-bit) locally via MLX to process audio and screen context without cloud routing.

Google Gemma

34,657 Aufrufe • vor 1 Monat

🔴 The Pain: Running local MLX models is incredibly fast and private. But let's be real - testing tool calling via terminal is clunky, and there's zero good UI for it. 🟢 The Fix: rapid-mlx share Just ONE command gives you a polished web chat + seamless tool calling (works beautifully with gemma-4-12b-qat). We are proud to be the ONLY MLX inference engine in the community shipping this. ⚡️ 👇 Try it now: brew install raullenchai/rapid-mlx/rapid-mlx

🔴 The Pain: Running local MLX models is incredibly fast and private. But let's be real - testing tool calling via terminal is clunky, and there's zero good UI for it. 🟢 The Fix: rapid-mlx share Just ONE command gives you a polished web chat + seamless tool calling (works beautifully with gemma-4-12b-qat). We are proud to be the ONLY MLX inference engine in the community shipping this. ⚡️ 👇 Try it now: brew install raullenchai/rapid-mlx/rapid-mlx

raullen

22,768 Aufrufe • vor 3 Monaten

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.

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

3,560,817 Aufrufe • vor 7 Monaten

🗓️ Release Week Recap Big week. mlx-audio and mlx-vlm are now among some of the fastest-growing OSS projects. Here’s what we shipped last week. Gemma 4 on Apple Silicon Two awesome releases by our partner Google DeepMind & Google Gemma : > Gemma 4 12B — their new dense, unified multimodal model. It uses an encoder free audio path and simplified vision encoder. > Gemma 4 QAT — quantization-aware training checkpoints, optimized to run locally on consumer GPUs and edge devices, compressing the model while preserving the quality you expect from Gemma 4. On the audio 🎧 side we added support for 15+ new TTS, ASR & VAD models, faster long-form transcription, and an expanded OpenAI-compatible audio server. All local on Apple Silicon. Huge thanks to every contributor and my co-maintainer Lucas Newman. 🙏🏽

🗓️ Release Week Recap Big week. mlx-audio and mlx-vlm are now among some of the fastest-growing OSS projects. Here’s what we shipped last week. Gemma 4 on Apple Silicon Two awesome releases by our partner Google DeepMind & Google Gemma : > Gemma 4 12B — their new dense, unified multimodal model. It uses an encoder free audio path and simplified vision encoder. > Gemma 4 QAT — quantization-aware training checkpoints, optimized to run locally on consumer GPUs and edge devices, compressing the model while preserving the quality you expect from Gemma 4. On the audio 🎧 side we added support for 15+ new TTS, ASR & VAD models, faster long-form transcription, and an expanded OpenAI-compatible audio server. All local on Apple Silicon. Huge thanks to every contributor and my co-maintainer Lucas Newman. 🙏🏽

Prince Canuma

11,810 Aufrufe • vor 3 Monaten

The latest MLX has a CUDA back-end! To get started: pip install "mlx[cuda]" With the same codebase you can develop locally, run your model on Apple silicon, or in the cloud on Nvidia GPUs. MLX is designed around Apple silicon - which has a unified memory architecture. It uses the same design with CUDA. So there's no need to move arrays around from CPU memory to GPU memory. Note, this is early days - some operations are missing and performance is still being optimized. But it's already quite fast for Transformer training, text generation, and more! Here's a demo using mlx-lm to generate text with Llama 3 8B (bf16) on an A100:

The latest MLX has a CUDA back-end! To get started: pip install "mlx[cuda]" With the same codebase you can develop locally, run your model on Apple silicon, or in the cloud on Nvidia GPUs. MLX is designed around Apple silicon - which has a unified memory architecture. It uses the same design with CUDA. So there's no need to move arrays around from CPU memory to GPU memory. Note, this is early days - some operations are missing and performance is still being optimized. But it's already quite fast for Transformer training, text generation, and more! Here's a demo using mlx-lm to generate text with Llama 3 8B (bf16) on an A100:

Awni Hannun

42,810 Aufrufe • vor 1 Jahr

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

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 Aufrufe • vor 4 Monaten

GPT 5.6 Sol turned my Daylight DC-1 into Tom Riddle's diary from Harry Potter. My prompts fade, OCR with Apple's Vision framework + Gemma 4 31B + Ollama respond. Everything locally on my Macbook. Watch till the end and volume up! Magical and inspired by Maxime Rivest 🧙‍♂️🦙🐧 work 🙏

GPT 5.6 Sol turned my Daylight DC-1 into Tom Riddle's diary from Harry Potter. My prompts fade, OCR with Apple's Vision framework + Gemma 4 31B + Ollama respond. Everything locally on my Macbook. Watch till the end and volume up! Magical and inspired by Maxime Rivest 🧙‍♂️🦙🐧 work 🙏

Ivan Fioravanti ᯅ

21,088 Aufrufe • vor 2 Monaten

This is MiniMax-M2.5 MLX running in LM Studio on an Apple Mac Studio M3 Ultra 512GB. Fast enough out of the box for hosting OpenClaw, n8n workflows, and Open WebUI for the team.

This is MiniMax-M2.5 MLX running in LM Studio on an Apple Mac Studio M3 Ultra 512GB. Fast enough out of the box for hosting OpenClaw, n8n workflows, and Open WebUI for the team.

Patrick J Kennedy

76,702 Aufrufe • vor 7 Monaten

ParoQuant just got a big upgrade 🚀 ✅ Supports the new Qwen3.5 models ⚡ Now runs on MLX (fast local inference on Apple Silicon) 🧠 Preserves reasoning quality with 4-bit quantization We also built an agent demo running locally on my 4-year-old M2 Max. Can't wait to upgrade to an M5 Max and see what kind of magic we can do. ✨

ParoQuant just got a big upgrade 🚀 ✅ Supports the new Qwen3.5 models ⚡ Now runs on MLX (fast local inference on Apple Silicon) 🧠 Preserves reasoning quality with 4-bit quantization We also built an agent demo running locally on my 4-year-old M2 Max. Can't wait to upgrade to an M5 Max and see what kind of magic we can do. ✨

Zhijian Liu

49,826 Aufrufe • vor 6 Monaten

You can now vibecode your own WisprFlow or Monologue alternative that runs completely locally on Apple Silicon using MLX-Audio-Swift 🔥 Check out this live transcription of Dwarkesh Patel interview with Andrej Karpathy using Qwen3-ASR-0.6B quantized to 4bit on a M3 Max. It also runs in realtime on a iPhone 15 Pro and iPad Pro M1. No cloud. No API keys.

You can now vibecode your own WisprFlow or Monologue alternative that runs completely locally on Apple Silicon using MLX-Audio-Swift 🔥 Check out this live transcription of Dwarkesh Patel interview with Andrej Karpathy using Qwen3-ASR-0.6B quantized to 4bit on a M3 Max. It also runs in realtime on a iPhone 15 Pro and iPad Pro M1. No cloud. No API keys.

Prince Canuma

60,974 Aufrufe • vor 7 Monaten

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! 💪

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

19,420 Aufrufe • vor 5 Monaten

PEOPLE ARE NOW RUNNING CLAUDE CODE WITH LOCAL AI MODELS TO AVOID API COSTS. By connecting tools like Ollama and Gemma 4, developers can build apps locally with unlimited usage and no monthly billing.

PEOPLE ARE NOW RUNNING CLAUDE CODE WITH LOCAL AI MODELS TO AVOID API COSTS. By connecting tools like Ollama and Gemma 4, developers can build apps locally with unlimited usage and no monthly billing.

0xMarioNawfal

158,585 Aufrufe • vor 5 Monaten