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.

AN $8 ESP32 IS RUNNING LOCAL AI WITH ZERO LATENCY A creator deployed a computer vision model on an ESP32 microcontroller to track human movement locally in real time, showing what’s possible without a GPU.

0xMarioNawfal

258,620 subscribers

58,032 views • 19 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

MotionStream Real-Time Video Generation with Interactive Motion Controls model runs in real time on a single NVIDIA H100 GPU (29 FPS, 0.4s Latency)

MotionStream Real-Time Video Generation with Interactive Motion Controls model runs in real time on a single NVIDIA H100 GPU (29 FPS, 0.4s Latency)

AK

22,304 views • 9 months ago

AI deployed Robotic Traffic cones. A road could have 1000s to respond to an emergency situation in real-time. ConeBot is on the job…

AI deployed Robotic Traffic cones. A road could have 1000s to respond to an emergency situation in real-time. ConeBot is on the job…

Brian Roemmele

57,799 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 • 10 months ago

I received a message in my direct messages asking how difficult it would be to use computer vision to track cell movement. > SAM zero shot for the immune cell > YOLO finetuned on a small dataset for bacteria Realization time: ~2 hours

I received a message in my direct messages asking how difficult it would be to use computer vision to track cell movement. > SAM zero shot for the immune cell > YOLO finetuned on a small dataset for bacteria Realization time: ~2 hours

Marco Franzon

188,212 views • 2 months ago

ABot World 0.5B is out! we have now world models at home, running in real-time on consumer GPU feed it an initial image, steer it with with your keyboard 🌎 you can run it locally or play now on spaces ▶️

ABot World 0.5B is out! we have now world models at home, running in real-time on consumer GPU feed it an initial image, steer it with with your keyboard 🌎 you can run it locally or play now on spaces ▶️

Hugging Apps

140,628 views • 18 days ago

I 3D printed a ship wheel that’s connected to a rotary encoder + ESP32. It connects to a local WebSocket server to send updates. On the right is a PI3 acting as a server, hosting multiple WebSocket servers to connect devices and also AI requests

I 3D printed a ship wheel that’s connected to a rotary encoder + ESP32. It connects to a local WebSocket server to send updates. On the right is a PI3 acting as a server, hosting multiple WebSocket servers to connect devices and also AI requests

Colin Duffy 🇺🇦

10,294 views • 3 months ago

"I'm not a human." Fed it to Qwen 3.5 0.8B running locally on my Mac Studio M2 Ultra. It solved it. The CAPTCHA is fake. But sending images to the local model? Very real. I'm not breaking the internet. Yet.

"I'm not a human." Fed it to Qwen 3.5 0.8B running locally on my Mac Studio M2 Ultra. It solved it. The CAPTCHA is fake. But sending images to the local model? Very real. I'm not breaking the internet. Yet.

stevibe

69,433 views • 5 months ago

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.

Adrien Grondin

12,045 views • 2 months ago

forget the $699 AI pins. this $8 chip just shattered the barrier for local AI hardware. a developer just forced a 28.9 million-parameter LLM onto a standard ESP32-S3 microcontroller. it costs roughly 8 dollars, runs completely offline, and draws the power of a single LED. conventional wisdom said a model of this size simply would not fit. the chip only has 512 KB of fast SRAM and 16 MB of flash. the breakthrough is architectural. the developer moved the bulk of the embedding table into flash memory and memory-mapped it. the chip only needs to pull about 450 bytes per token, keeping the active working memory inside the fast SRAM. this means you can now embed a capable language model into a physical node for the price of two coffees. and we are already seeing the beginnings of this custom physical hardware. in the video, a creator built a minimalist voice-controlled universal remote using an ESP32. it captures voice and remotely controls the computer over bluetooth LE. he simply says "open chrome and open 20 new tabs", and the custom hardware executes it instantly. we have spent years watching model sizes explode upward. but the true frontier is the opposite direction. when an eight-dollar chip can power offline intelligence and custom physical interfaces, AI becomes local infrastructure rather than a cloud service.

forget the $699 AI pins. this $8 chip just shattered the barrier for local AI hardware. a developer just forced a 28.9 million-parameter LLM onto a standard ESP32-S3 microcontroller. it costs roughly 8 dollars, runs completely offline, and draws the power of a single LED. conventional wisdom said a model of this size simply would not fit. the chip only has 512 KB of fast SRAM and 16 MB of flash. the breakthrough is architectural. the developer moved the bulk of the embedding table into flash memory and memory-mapped it. the chip only needs to pull about 450 bytes per token, keeping the active working memory inside the fast SRAM. this means you can now embed a capable language model into a physical node for the price of two coffees. and we are already seeing the beginnings of this custom physical hardware. in the video, a creator built a minimalist voice-controlled universal remote using an ESP32. it captures voice and remotely controls the computer over bluetooth LE. he simply says "open chrome and open 20 new tabs", and the custom hardware executes it instantly. we have spent years watching model sizes explode upward. but the true frontier is the opposite direction. when an eight-dollar chip can power offline intelligence and custom physical interfaces, AI becomes local infrastructure rather than a cloud service.

ard

424,888 views • 23 days ago

I love this opensource project! Someone just put a 28.9M parameter AI model on an ESP32-S3. A chip that costs only a few dollars. No cloud. No API. No internet. It runs locally at ~9.5 tokens/s and can generate stories on a tiny screen. This changes the way we think about AI hardware. The next generation of AI toys, robots, and IoT devices may not need the cloud at all. Small chips are getting smarter. 🤖

I love this opensource project! Someone just put a 28.9M parameter AI model on an ESP32-S3. A chip that costs only a few dollars. No cloud. No API. No internet. It runs locally at ~9.5 tokens/s and can generate stories on a tiny screen. This changes the way we think about AI hardware. The next generation of AI toys, robots, and IoT devices may not need the cloud at all. Small chips are getting smarter. 🤖

Steven Cheng

104,329 views • 15 days ago

Just wrapped up a local meetup teaching people how to build their MVP in an hour using Replit ⠕. Participants walked out with their first web/mobile app and a new appreciation for what’s possible with AI.

Just wrapped up a local meetup teaching people how to build their MVP in an hour using Replit ⠕. Participants walked out with their first web/mobile app and a new appreciation for what’s possible with AI.

Raymmar

12,390 views • 3 months ago

A real-time AI motion capture model with 1B parameters. Connects to a 1080P camera or processes uploaded video to generate 3D motion data in real time. Supports Unreal Engine, Unity, and Blender, requiring 8GB of GPU VRAM for real-time processing.

A real-time AI motion capture model with 1B parameters. Connects to a 1080P camera or processes uploaded video to generate 3D motion data in real time. Supports Unreal Engine, Unity, and Blender, requiring 8GB of GPU VRAM for real-time processing.

CYANPUPPETS

36,950 views • 5 months ago

Depth Anything V2 is a total beast for real-time 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).

Depth Anything V2 is a total beast for real-time 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).

Gábor Pribék

142,321 views • 3 months ago

Gemma 4 analyzes the video. Generates key questions. Calls Falcon Perception. "Find all the people." 156 found. "Detect only white cars." 8 found. A 26B model is running agentic multi-QA vision orchestration. The models are running locally on a MacBook with MLX. No API.

Gemma 4 analyzes the video. Generates key questions. Calls Falcon Perception. "Find all the people." 156 found. "Detect only white cars." 8 found. A 26B model is running agentic multi-QA vision orchestration. The models are running locally on a MacBook with MLX. No API.

Maziyar PANAHI

158,918 views • 4 months ago

Gemma 4 just dropped. I had it captioning video in real-time within an hour. Running locally on a MacBook. No cloud. No API. Real-time scene understanding. Oh and SAM3 is segmenting every object in the same frame. Same laptop.

Gemma 4 just dropped. I had it captioning video in real-time within an hour. Running locally on a MacBook. No cloud. No API. Real-time scene understanding. Oh and SAM3 is segmenting every object in the same frame. Same laptop.

Maziyar PANAHI

196,846 views • 4 months ago

this guy 3D printed and vibe coded a tiny Claude robot for his desk it's called "Clawd Mochi." runs on an ESP32 chip with a tiny display that shows animated expressions. > hosts its own WiFi hotspot. zero cloud and zero internet required. fully offline > live-switch between animated faces, a terminal emulator, and a drawing canvas from your browser > total cost: under $8 > takes less than an hour to build 3D print files AND the full build are both open source too this is the greatest thing anyone has built with vibe coding

this guy 3D printed and vibe coded a tiny Claude robot for his desk it's called "Clawd Mochi." runs on an ESP32 chip with a tiny display that shows animated expressions. > hosts its own WiFi hotspot. zero cloud and zero internet required. fully offline > live-switch between animated faces, a terminal emulator, and a drawing canvas from your browser > total cost: under $8 > takes less than an hour to build 3D print files AND the full build are both open source too this is the greatest thing anyone has built with vibe coding

Om Patel

154,373 views • 4 months ago

Cool new work on real-time video generation with motion control. MotionStream enables sub-second latency streaming on a single GPU. You can also control what parts of an image do & don't move, like the video below. 👏 to Xun Huang, Joonghyuk Shin, and team!

Cool new work on real-time video generation with motion control. MotionStream enables sub-second latency streaming on a single GPU. You can also control what parts of an image do & don't move, like the video below. 👏 to Xun Huang, Joonghyuk Shin, and team!

Justine Moore

21,780 views • 9 months ago

Wow! This is amazing! Segmented every car locally in real time with Meta's SAM3 converted to MLX. Just on-device (M2 laptop) vision getting absurdly good. Local AI is moving faster than most people realize! What other models should we test? what kind of videos?

Wow! This is amazing! Segmented every car locally in real time with Meta's SAM3 converted to MLX. Just on-device (M2 laptop) vision getting absurdly good. Local AI is moving faster than most people realize! What other models should we test? what kind of videos?

Maziyar PANAHI

177,270 views • 4 months ago

Is it time to made an experimental action film about young Asian femme fatale? 🤸‍♀️ I’m experimenting with a single, consistent character executing movement shots—running, jumping, crouching, and swinging a sword—using the AI tools Midjourney and Hailuo AI (MiniMax) .

Is it time to made an experimental action film about young Asian femme fatale? 🤸‍♀️ I’m experimenting with a single, consistent character executing movement shots—running, jumping, crouching, and swinging a sword—using the AI tools Midjourney and Hailuo AI (MiniMax) .

Junie Lau

20,540 views • 1 year ago

generate an artifact in Midjourney turn into a 3D model with 3DAIStudio 3D print the AI artifact on an UltiMaker generate paint ideas using retexture in MJ paint the artifact with acrylics AI to real life and back again

generate an artifact in Midjourney turn into a 3D model with 3DAIStudio 3D print the AI artifact on an UltiMaker generate paint ideas using retexture in MJ paint the artifact with acrylics AI to real life and back again

Nick St. Pierre

75,545 views • 1 year ago