Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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

Adrien Grondin

8,386 subscribers

441,385 views • 2 days ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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

Adrien Grondin

1,565,867 views • 1 year ago

How does Edge0 run a 35B model with only 1–2.5 GB of peak memory? In simple terms: • The full model stays in storage. • Only the parameters needed for the current step are loaded into memory. • The next parameters are prepared while the current step is running. • Memory is reused instead of loading the entire model at once. Large model. Small working set. Fully on-device.

How does Edge0 run a 35B model with only 1–2.5 GB of peak memory? In simple terms: • The full model stays in storage. • Only the parameters needed for the current step are loaded into memory. • The next parameters are prepared while the current step is running. • Memory is reused instead of loading the entire model at once. Large model. Small working set. Fully on-device.

Samuel Zeng

34,026 views • 7 days ago

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

Adrien Grondin

493,561 views • 11 months ago

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

Adrien Grondin

13,376 views • 1 month ago

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

Adrien Grondin

67,095 views • 2 months ago

Happy Friday! We just put DeepSeek-V4-Pro up on It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →

Happy Friday! We just put DeepSeek-V4-Pro up on It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →

NVIDIA AI

206,686 views • 4 months ago

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

Adrien Grondin

907,443 views • 11 months ago

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

Adrien Grondin

1,045,258 views • 5 months ago

1/ Any model on OpenRouter can now run code in a hosted Linux container. Add one tool to a Responses API request. The model writes the script, runs it, and reads back the result. Nothing to install, nothing to host. Meet openrouter:shell. To get started: "tools": [{ "type": "openrouter:shell", "parameters": { "engine": "openrouter" } }]

1/ Any model on OpenRouter can now run code in a hosted Linux container. Add one tool to a Responses API request. The model writes the script, runs it, and reads back the result. Nothing to install, nothing to host. Meet openrouter:shell. To get started: "tools": [{ "type": "openrouter:shell", "parameters": { "engine": "openrouter" } }]

OpenRouter

26,849 views • 18 hours ago

🚨 do you understand what happened to Apple.. Apple just announced Siri AI at WWDC 2026. The new "revolutionary" assistant is literally Google Gemini running in a costume. - Apple pays Google 1 billion dollars a year for a custom 1.2 trillion parameter Gemini model - the only Apple part of Siri AI is the logo and the privacy marketing - Siri AI launches in fall 2026 and only works on iPhone 15 Pro and newer - Tim Cook leaves as CEO on September 1, three weeks before it ships the company that used to be the most valuable on earth couldn't build its own AI and had to rent one from the search engine.

BuBBliK

144,663 views • 3 months ago

The new Laguna S 2.1 model by Poolside is now free for 2 weeks on Nous Portal. At 118B total parameters with 8B active, it's quick to run and the most capable model they've released so far. Try Portal today at

The new Laguna S 2.1 model by Poolside is now free for 2 weeks on Nous Portal. At 118B total parameters with 8B active, it's quick to run and the most capable model they've released so far. Try Portal today at

Nous Research

195,765 views • 1 month ago

DeepSeek R1 distilled to Qwen 1.5B easily runs on my iPhone 16 with MLX swift. Here's the 4-bit model reasoning entirely on device at almost 60 toks/sec:

DeepSeek R1 distilled to Qwen 1.5B easily runs on my iPhone 16 with MLX swift. Here's the 4-bit model reasoning entirely on device at almost 60 toks/sec:

Awni Hannun

1,139,934 views • 1 year ago

it's crazy what a 1.5B model can do these days! "VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium." runs perfectly on device!

it's crazy what a 1.5B model can do these days! "VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium." runs perfectly on device!

Maziyar PANAHI

202,387 views • 10 months ago

🔥 GLM-5.3-Flash Hits #1 on 🐮 GLM-5.3-Flash (Ox Alpha) is now the most-used and most popular model on with cumulative token throughput surpassing 2.41 trillion tokens. As the first native omni-modal model in the GLM-5 series, it packs 320B total parameters, with 18B active, and features a hybrid sparse and linear attention architecture with a 1M-token context window. The result: lightning-fast responses, powerful reasoning, and outstanding cost efficiency. 🎁 Still 100% FREE on From high-frequency API calls and coding to complex Agents and long-document processing, jump in and experience the #1 model on for yourself! 👉 Try it free now:

🔥 GLM-5.3-Flash Hits #1 on 🐮 GLM-5.3-Flash (Ox Alpha) is now the most-used and most popular model on with cumulative token throughput surpassing 2.41 trillion tokens. As the first native omni-modal model in the GLM-5 series, it packs 320B total parameters, with 18B active, and features a hybrid sparse and linear attention architecture with a 1M-token context window. The result: lightning-fast responses, powerful reasoning, and outstanding cost efficiency. 🎁 Still 100% FREE on From high-frequency API calls and coding to complex Agents and long-document processing, jump in and experience the #1 model on for yourself! 👉 Try it free now:

B.AI

218,306 views • 12 days ago

Made with Gemini AI Introducing iPhone 17 Pro 🧡📱 A bold visual concept built around Pro performance, advanced cameras, and cinematic storytelling. Video Prompt 👇👇 Shot 1 Bold Opening Start with a powerful orange background and huge PRO typography. The iPhone 17 Pro enters the frame with a dramatic camera push-in. Shot 2 Lifestyle Hero Low-angle fashion shot of the model holding the iPhone 17 Pro toward the camera. Orange cap, modern streetwear, bold lighting, confident attitude. Shot 3 Camera Detail Extreme macro close-up of the iPhone 17 Pro camera system. Smooth rotation around the lenses with sharp reflections and premium product lighting. Shot 4 Performance Visual Show the phone surrounded by dynamic light trails and subtle motion graphics representing powerful performance. Keep the device crisp and centered. Shot 5 Pro Camera Experience Model captures cinematic footage with the iPhone. Transition from the phone screen to the real scene being filmed, highlighting a professional creator aesthetic. Shot 6 Cinematic Video Show a smooth sequence of the model walking through an urban environment while filming. Dynamic tracking camera, natural movement, premium smartphone-ad feel. Shot 7 Apple Intelligence Moment Close-up of the iPhone display showing an intelligent feature in action. Clean interface, subtle animations, modern orange environment. Shot 8 Final Product Reveal The iPhone 17 Pro floats against a vibrant orange background. Camera slowly circles the device before landing on the camera module. Shot 9 Final Frame Bold iPhone 17 Pro typography appears alongside the hero device, with a clean premium finish and dramatic lighting. Overall style: bold orange campaign, premium smartphone advertising, fashion + technology aesthetic, cinematic camera movements, realistic product details, glossy highlights, high-energy commercial visuals.

Made with Gemini AI Introducing iPhone 17 Pro 🧡📱 A bold visual concept built around Pro performance, advanced cameras, and cinematic storytelling. Video Prompt 👇👇 Shot 1 Bold Opening Start with a powerful orange background and huge PRO typography. The iPhone 17 Pro enters the frame with a dramatic camera push-in. Shot 2 Lifestyle Hero Low-angle fashion shot of the model holding the iPhone 17 Pro toward the camera. Orange cap, modern streetwear, bold lighting, confident attitude. Shot 3 Camera Detail Extreme macro close-up of the iPhone 17 Pro camera system. Smooth rotation around the lenses with sharp reflections and premium product lighting. Shot 4 Performance Visual Show the phone surrounded by dynamic light trails and subtle motion graphics representing powerful performance. Keep the device crisp and centered. Shot 5 Pro Camera Experience Model captures cinematic footage with the iPhone. Transition from the phone screen to the real scene being filmed, highlighting a professional creator aesthetic. Shot 6 Cinematic Video Show a smooth sequence of the model walking through an urban environment while filming. Dynamic tracking camera, natural movement, premium smartphone-ad feel. Shot 7 Apple Intelligence Moment Close-up of the iPhone display showing an intelligent feature in action. Clean interface, subtle animations, modern orange environment. Shot 8 Final Product Reveal The iPhone 17 Pro floats against a vibrant orange background. Camera slowly circles the device before landing on the camera module. Shot 9 Final Frame Bold iPhone 17 Pro typography appears alongside the hero device, with a clean premium finish and dramatic lighting. Overall style: bold orange campaign, premium smartphone advertising, fashion + technology aesthetic, cinematic camera movements, realistic product details, glossy highlights, high-energy commercial visuals.

𝐒𝐊_𝐀𝐈

117,218 views • 18 days ago

Amazing Ukrainian ingenuity. This is the cheapest way to neutralize russian threats. Ukrainian interceptor drones such as the Wild Hornets STING and SkyFall P1-SUN typically cost around $1,000–2,500 per unit, depending on the model and configuration. Meanwhile, the russian Shahed-type drones cost around $20,000–$70,000 per unit, depending on the model and configuration. The return on investment is 20 to 1.

Amazing Ukrainian ingenuity. This is the cheapest way to neutralize russian threats. Ukrainian interceptor drones such as the Wild Hornets STING and SkyFall P1-SUN typically cost around $1,000–2,500 per unit, depending on the model and configuration. Meanwhile, the russian Shahed-type drones cost around $20,000–$70,000 per unit, depending on the model and configuration. The return on investment is 20 to 1.

Roman Sheremeta 🇺🇸🇺🇦

3,167,974 views • 3 months ago

A few months ago, we introduced our AI 3D Model Generator on web. Today, the AI Capture feature is available on iOS! 🤳 Photo to 3D model instantly. Straight from your phone. Upload or capture in-app. 3D creation has never been this simple.

A few months ago, we introduced our AI 3D Model Generator on web. Today, the AI Capture feature is available on iOS! 🤳 Photo to 3D model instantly. Straight from your phone. Upload or capture in-app. 3D creation has never been this simple.

polycam

13,148 views • 1 year ago

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

Sundar Pichai

864,698 views • 1 year ago