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.

Live AI Object Segmentation with the Raspberry Pi 5 and the HAILO AI Accelerator Hat+ with 26 TOPS

SparkLab

1,245 subscribers

61,819 views • 4 months 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

THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM. that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks. the fine print: the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70 and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not. why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none. the honest caveats, both ways: the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress "small" is the load-bearing word. don't expect gpt at home on a pi the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load. no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think. save this before you buy the wrong kit for the word on the box.

THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM. that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks. the fine print: the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70 and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not. why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none. the honest caveats, both ways: the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress "small" is the load-bearing word. don't expect gpt at home on a pi the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load. no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think. save this before you buy the wrong kit for the word on the box.

RetroChainer

11,100 views • 1 month ago

Play around with programmable input/output for your Raspberry Pi 5.

Play around with programmable input/output for your Raspberry Pi 5.

Raspberry Pi

19,979 views • 1 year ago

Running minecraft on a raspberry pi 5 with a circular screen hehe

Running minecraft on a raspberry pi 5 with a circular screen hehe

˗ˏˋmewtru´ˎ˗

32,751 views • 5 months ago

A $90 Raspberry Pi can run a fully offline AI assistant that never touches the internet. Source: Technology Brief

A $90 Raspberry Pi can run a fully offline AI assistant that never touches the internet. Source: Technology Brief

Big Brain AI

58,282 views • 2 months ago

This is Thumby, the worlds smallest game player which runs on Linux with a Raspberry Pi processor.

This is Thumby, the worlds smallest game player which runs on Linux with a Raspberry Pi processor.

Massimo

23,820 views • 11 months ago

YOLOE-26 released by Ultralytics support text + visual prompts 🤯 This was a part of the YOLO26 release. It's a zero-shot, promotable model, almost like YOLO-World, but it also offers real-time object segmentation. Highlights👇 #AI #MachineLearning #YOLOE

YOLOE-26 released by Ultralytics support text + visual prompts 🤯 This was a part of the YOLO26 release. It's a zero-shot, promotable model, almost like YOLO-World, but it also offers real-time object segmentation. Highlights👇 #AI #MachineLearning #YOLOE

Muhammad Rizwan Munawar

35,311 views • 6 months ago

decided to build the instant cam from scratch with a raspberry pi + thermal printer - part 1: camera is working 😌

decided to build the instant cam from scratch with a raspberry pi + thermal printer - part 1: camera is working 😌

tigris

10,301 views • 2 years ago

This lawyer made $150,000 selling portable offline AI. It analyzes docs that can’t legally be shown on the web. The whole setup costs $50 and he sells it for $999. Here's how to make one step-by-step: You need 4 things: → Raspberry Pi 5 (8GB) → PiSugar 3 Plus battery → Whisplay HAT for the screen and mic → 64GB SD card. Total cost on Ali is around $50 to $90 if you wait for the right deals. 1. Write Raspberry Pi OS Lite 64-bit to the SD card using Raspberry Pi Imager. 2. Stack the PiSugar battery underneath the Pi, snap the Whisplay HAT on top, insert the SD card, and boot the device. 3. Open the terminal and install Ollama with one command: curl -fsSL | sh 4. Pull a model that actually runs on the Pi without choking: ollama pull phi3:mini 5. Run the model and start chatting offline: ollama run phi3:mini The whole thing fits in your pocket, lasts 4 hours on battery, and never touches the internet once setup is done. The lawyer wraps his version in a custom case, preloads it with legal document analysis prompts, and sells it to law firms that can't legally process client data in the cloud. You can sell yours to doctors, accountants, government contractors, defense companies, or anyone else who handles data that legally cannot leave the building. Hardware cost: $50 to $90. Selling price: $500 to $1999

This lawyer made $150,000 selling portable offline AI. It analyzes docs that can’t legally be shown on the web. The whole setup costs $50 and he sells it for $999. Here's how to make one step-by-step: You need 4 things: → Raspberry Pi 5 (8GB) → PiSugar 3 Plus battery → Whisplay HAT for the screen and mic → 64GB SD card. Total cost on Ali is around $50 to $90 if you wait for the right deals. 1. Write Raspberry Pi OS Lite 64-bit to the SD card using Raspberry Pi Imager. 2. Stack the PiSugar battery underneath the Pi, snap the Whisplay HAT on top, insert the SD card, and boot the device. 3. Open the terminal and install Ollama with one command: curl -fsSL | sh 4. Pull a model that actually runs on the Pi without choking: ollama pull phi3:mini 5. Run the model and start chatting offline: ollama run phi3:mini The whole thing fits in your pocket, lasts 4 hours on battery, and never touches the internet once setup is done. The lawyer wraps his version in a custom case, preloads it with legal document analysis prompts, and sells it to law firms that can't legally process client data in the cloud. You can sell yours to doctors, accountants, government contractors, defense companies, or anyone else who handles data that legally cannot leave the building. Hardware cost: $50 to $90. Selling price: $500 to $1999

Coin Shot ☁️

199,858 views • 3 months ago

MyShell Testnet ◤Phase 01◢ is Live! Join the revolution and (open, AI) with us:

MyShell Testnet ◤Phase 01◢ is Live! Join the revolution and (open, AI) with us:

MyShell.AI

315,850 views • 2 years ago

🚨 A new member joins the Raspberry Pi 5 family 🚨 With 2GB of RAM, and priced at just $50, this new entry-level product continues our mission to reduce the cost of high-performance general-purpose computing. Read me:

🚨 A new member joins the Raspberry Pi 5 family 🚨 With 2GB of RAM, and priced at just $50, this new entry-level product continues our mission to reduce the cost of high-performance general-purpose computing. Read me:

Raspberry Pi

106,331 views • 2 years ago

Pi Network Spotlights SoloHost’s Local AI Potential Pi Network (Pi Network) is expanding what users can do with their computers through SoloHost. Pi Network says SoloHost could give Pioneers more control over local computing. The platform supports local AI agents and specialized self hosted software. That includes tools such as OpenClaw and Atlassian MCP Server. The initiative could make Pi Desktop and Nodes useful beyond blockchain infrastructure. Pi says local computing can reduce dependence on third party services.

Pi Network Spotlights SoloHost’s Local AI Potential Pi Network (Pi Network) is expanding what users can do with their computers through SoloHost. Pi Network says SoloHost could give Pioneers more control over local computing. The platform supports local AI agents and specialized self hosted software. That includes tools such as OpenClaw and Atlassian MCP Server. The initiative could make Pi Desktop and Nodes useful beyond blockchain infrastructure. Pi says local computing can reduce dependence on third party services.

BSCN

33,647 views • 6 days ago

another experiment with fruit, computer vision, and projection mapping live object detections (roboflow RF-DETR model) are used to control the animated scene (threejs) i also added mediapipe segmentation to the pipeline to create collisions with my silhouette, but i haven't gotten a hang of it yet more experiments are underway

another experiment with fruit, computer vision, and projection mapping live object detections (roboflow RF-DETR model) are used to control the animated scene (threejs) i also added mediapipe segmentation to the pipeline to create collisions with my silhouette, but i haven't gotten a hang of it yet more experiments are underway

AA

21,581 views • 3 months ago

Pi Network Makes New Push For AI Developers Pi Network (Pi Network) has outlined how users can introduce Pi to AI developers ahead of Pi2Day on June 28. Pioneers can win Pi merchandise by posting about Pi in vibe coder communities and submitting links through the Pi app. The push centres on Pi App Studio, which lets developers plug existing AI-built apps into Pi's ecosystem. Pi claims its network gives builders instant access to 60 million users, plus built-in payments, identity and ads infrastructure.

Pi Network Makes New Push For AI Developers Pi Network (Pi Network) has outlined how users can introduce Pi to AI developers ahead of Pi2Day on June 28. Pioneers can win Pi merchandise by posting about Pi in vibe coder communities and submitting links through the Pi app. The push centres on Pi App Studio, which lets developers plug existing AI-built apps into Pi's ecosystem. Pi claims its network gives builders instant access to 60 million users, plus built-in payments, identity and ads infrastructure.

BSCN

39,984 views • 2 months ago

Run promptable segmentation with Ultralytics YOLO26-E! 🧠 Segment objects using natural language prompts with YOLO26-E, ideal for flexible visual search, rapid annotation, and interactive computer vision workflows. #MachineLearning #AI #Research

Run promptable segmentation with Ultralytics YOLO26-E! 🧠 Segment objects using natural language prompts with YOLO26-E, ideal for flexible visual search, rapid annotation, and interactive computer vision workflows. #MachineLearning #AI #Research

Muhammad Rizwan Munawar

23,386 views • 2 months ago

Awesome way to AI is here! Meet the latest Samsung Galaxy A17 5G, packed with core AI features like Gemini Live and Circle to Search. What you couldn’t earlier, Now you can with the new awesome!

Awesome way to AI is here! Meet the latest Samsung Galaxy A17 5G, packed with core AI features like Gemini Live and Circle to Search. What you couldn’t earlier, Now you can with the new awesome!

Samsung India

855,478 views • 1 year ago

Pi is going to pay for robots Pi Network (Pi Network) has joined RoboPay as a payment partner, with $PI set to be used for robot services across the Fabric network (Fabric Foundation). RoboPay was built so AI agents can discover, hire and pay robots autonomously onchain, and this deal extends that same rail to tens of millions of Pi holders. Once services go live, the vision includes summoning delivery robots for groceries, dispatching security patrols, or booking industrial inspections, all paid in the currency Pioneers already hold. Fabric calls it the foundation of an open machine economy where humans, AI and robots transact side by side.

Pi is going to pay for robots Pi Network (Pi Network) has joined RoboPay as a payment partner, with $PI set to be used for robot services across the Fabric network (Fabric Foundation). RoboPay was built so AI agents can discover, hire and pay robots autonomously onchain, and this deal extends that same rail to tens of millions of Pi holders. Once services go live, the vision includes summoning delivery robots for groceries, dispatching security patrols, or booking industrial inspections, all paid in the currency Pioneers already hold. Fabric calls it the foundation of an open machine economy where humans, AI and robots transact side by side.

BSCN

60,314 views • 1 month ago