Loading video...

Video Failed to Load

Go Home

Introducing FunctionGemma 🤏270m model for function calling 📱can run in your phone, browser or other devices 🤖designed to be specialized for your own tasks

osanseviero's profile picture

Omar Sanseviero 🇫🇷 @RAISE Paris

70,921 subscribers

302,179 views • 8 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

NEW: Google releases FunctionGemma, a lightweight (270M), open foundation model built for creating specialized function calling models! 🤯 To test it out, I built a small game: use natural language to solve fun physics simulation puzzles, running 100% locally in your browser! 🕹️
3:17

NEW: Google releases FunctionGemma, a lightweight (270M), open foundation model built for creating specialized function calling models! 🤯 To test it out, I built a small game: use natural language to solve fun physics simulation puzzles, running 100% locally in your browser! 🕹️

Xenova

58,200 views • 8 months ago

Google just released their smallest Gemma model ever: Gemma 3 270M! 🤯 🤏 Highly compact & efficient 🤖 Strong instruction-following capabilities 🔧 Perfect candidate for fine-tuning It's so tiny that it can even run 100% locally in your browser with Transformers.js! 🤗
1:42

Google just released their smallest Gemma model ever: Gemma 3 270M! 🤯 🤏 Highly compact & efficient 🤖 Strong instruction-following capabilities 🔧 Perfect candidate for fine-tuning It's so tiny that it can even run 100% locally in your browser with Transformers.js! 🤗

Xenova

34,738 views • 1 year ago

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇
0:26

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇

Xenova

25,302 views • 1 year ago

Browser Use is now available in SpaceXAI's Grok Build! Ask Grok to complete tasks for you, or have it test your websites and fix bugs. Grok Build can work in your own browser or one hosted in the cloud.
0:31

Browser Use is now available in SpaceXAI's Grok Build! Ask Grok to complete tasks for you, or have it test your websites and fix bugs. Grok Build can work in your own browser or one hosted in the cloud.

Browser Use

34,537 views • 12 days ago

Someone built a browser designed from the ground up for humans and AI agents to share. It's called ego lite. -Your agents run tasks in their own Spaces while your tabs stay yours -No extra setup - agents access your real logins and tabs directly through ego-browser -⁠Faster task completion on fewer tokens than any existing browser automation framework Every other tool makes you run a separate browser. This one just shares yours. Github:
0:28

Someone built a browser designed from the ground up for humans and AI agents to share. It's called ego lite. -Your agents run tasks in their own Spaces while your tabs stay yours -No extra setup - agents access your real logins and tabs directly through ego-browser -⁠Faster task completion on fewer tokens than any existing browser automation framework Every other tool makes you run a separate browser. This one just shares yours. Github:

0xMarioNawfal

51,758 views • 1 month ago

Not enough people are talking about NVIDIA's new Nemotron-3-Nano (4B) model! 🤯 Hybrid Mamba + Attention architecture, designed as a unified model for reasoning and non-reasoning tasks. So small and efficient, it can run 100% locally in your web browser at 75 tokens per second.
1:06

Not enough people are talking about NVIDIA's new Nemotron-3-Nano (4B) model! 🤯 Hybrid Mamba + Attention architecture, designed as a unified model for reasoning and non-reasoning tasks. So small and efficient, it can run 100% locally in your web browser at 75 tokens per second.

Xenova

50,063 views • 5 months ago

Open Source alternative to Apple Intelligence For small tasks, it runs LLM agents on-device. For larger tasks, it runs on your own AI cluster of personal devices Your data stays on your devices By exo intern
1:44

Open Source alternative to Apple Intelligence For small tasks, it runs LLM agents on-device. For larger tasks, it runs on your own AI cluster of personal devices Your data stays on your devices By exo intern

Mohamed Baioumy

142,817 views • 2 years ago

Introducing Giga's browser agent. Giga can now log in and completes tasks end-to-end, just like your human agents. It used to take months to get support APIs deployed for AI agents in the enterprise. Now these integrations can be built instantly.
1:16

Introducing Giga's browser agent. Giga can now log in and completes tasks end-to-end, just like your human agents. It used to take months to get support APIs deployed for AI agents in the enterprise. Now these integrations can be built instantly.

Esha

1,481,739 views • 7 months ago

Introducing /cookie-sync Run browser tasks in the cloud with all your authenticated accounts, powered by Browserbase Watch as my agent: - uploads my local Chrome cookies - injects them into a remote browser - goes to Forkable & chooses my Friday lunch for me
0:39

Introducing /cookie-sync Run browser tasks in the cloud with all your authenticated accounts, powered by Browserbase Watch as my agent: - uploads my local Chrome cookies - injects them into a remote browser - goes to Forkable & chooses my Friday lunch for me

Shrey Pandya

56,739 views • 5 months ago

Introducing emails for agents! 🤖💌 Starting today, Vellum Pro assistants get their own subdomain, handle, and inbox. CC them on emails, share your calendar, or let them run outbound for you
1:30

Introducing emails for agents! 🤖💌 Starting today, Vellum Pro assistants get their own subdomain, handle, and inbox. CC them on emails, share your calendar, or let them run outbound for you

Marina · vellum.ai 👾

36,560 views • 2 months ago

WOW! 🤯 DINOv3 can run locally on your phone... from the browser! This unlocks endless possibilities for AI-powered web apps. 🤏 Model is tiny (only 15MB at 4-bit quantization) 🧠 Delivers powerful, high-resolution image features ✨ Works completely offline Try it yourself 👇
0:22

WOW! 🤯 DINOv3 can run locally on your phone... from the browser! This unlocks endless possibilities for AI-powered web apps. 🤏 Model is tiny (only 15MB at 4-bit quantization) 🧠 Delivers powerful, high-resolution image features ✨ Works completely offline Try it yourself 👇

Xenova

39,221 views • 1 year ago

We released iOS app for Hermes Agent 📱 Connect to your self-hosted agent over Tailscale, Cloudflare Tunnel or ngrok. Or deploy on a VPS. Run tasks and manage your agent from anywhere.
0:31

We released iOS app for Hermes Agent 📱 Connect to your self-hosted agent over Tailscale, Cloudflare Tunnel or ngrok. Or deploy on a VPS. Run tasks and manage your agent from anywhere.

atomicbot.ai

111,089 views • 3 months ago

You can now run Claude Code tasks from the Claude Android app, in research preview. Kick off cloud-based tasks from your phone, let Claude run, then pick them up later to review and merge work. Download Claude for Android:
0:32

You can now run Claude Code tasks from the Claude Android app, in research preview. Kick off cloud-based tasks from your phone, let Claude run, then pick them up later to review and merge work. Download Claude for Android:

Claude

51,409 views • 8 months ago

If your AI can't call a function or hit an API, it's not really an agent (it's a chatbot). Vision Agents makes it simple to connect MCP servers and function calling so your model can interact with its surroundings: running code, fetching data, and automating tasks. Step-by-step implementation from Stefan in thread ⬇
0:25

If your AI can't call a function or hit an API, it's not really an agent (it's a chatbot). Vision Agents makes it simple to connect MCP servers and function calling so your model can interact with its surroundings: running code, fetching data, and automating tasks. Step-by-step implementation from Stefan in thread ⬇

Stream

31,306 views • 10 months ago

OMG… you can now fine-tune your own AI model and run it entirely on your device. No servers. No API keys. No data leaks. Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own. Here’s how:
0:23

OMG… you can now fine-tune your own AI model and run it entirely on your device. No servers. No API keys. No data leaks. Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own. Here’s how:

Louis Gleeson

79,508 views • 11 months ago

Can you stay in a Mansion without your phone 📱 for 24 Hours ?😨
2:59

Can you stay in a Mansion without your phone 📱 for 24 Hours ?😨

Mrbluemax

18,915 views • 1 month ago

new in Julius AI: we’re moving from a shared sandbox between tasks to a dedicated sandbox per task this means multiple tasks can now run in parallel without taking compute resources from your other tasks big compute boost for each task
1:15

new in Julius AI: we’re moving from a shared sandbox between tasks to a dedicated sandbox per task this means multiple tasks can now run in parallel without taking compute resources from your other tasks big compute boost for each task

rahul

95,609 views • 17 days ago

🚀 Introducing Queue: A Smarter Way to Build with Replit Agent Today, we’re excited to launch Queue, a powerful new capability designed to enhance your experience with Replit Agent. With Queue, you can submit multiple tasks while your Agent is still working—no more waiting around or breaking your flow. As each task completes, the Agent automatically moves to the next. You can: ✅ Add multiple tasks for the Agent to process in order. ✅ Edit, reorder, or reprioritize messages on the fly. ✅ Attach files and adjust settings—including toggling extended thinking or selecting a different model—per task.
0:27

🚀 Introducing Queue: A Smarter Way to Build with Replit Agent Today, we’re excited to launch Queue, a powerful new capability designed to enhance your experience with Replit Agent. With Queue, you can submit multiple tasks while your Agent is still working—no more waiting around or breaking your flow. As each task completes, the Agent automatically moves to the next. You can: ✅ Add multiple tasks for the Agent to process in order. ✅ Edit, reorder, or reprioritize messages on the fly. ✅ Attach files and adjust settings—including toggling extended thinking or selecting a different model—per task.

Replit ⠕

75,576 views • 1 year ago

Introducing Silent Speech interface for your existing devices! From your phone or computer, it lets you communicate with AI at the speed of voice, using only your mouth movements, no sound. Demo 0:13 and 1:09
2:42

Introducing Silent Speech interface for your existing devices! From your phone or computer, it lets you communicate with AI at the speed of voice, using only your mouth movements, no sound. Demo 0:13 and 1:09

Adam

103,162 views • 1 month ago

Introducing custom model routers. Set your own routing rules in plain english: - "Send simple requests to minimax" - "Send planning tasks to Claude" - "Send bug fixes to Kimi k3" And every prompt gets auto-routed to the right model for the job. Here's how to make one:
1:49

Introducing custom model routers. Set your own routing rules in plain english: - "Send simple requests to minimax" - "Send planning tasks to Claude" - "Send bug fixes to Kimi k3" And every prompt gets auto-routed to the right model for the job. Here's how to make one:

Warp

201,430 views • 1 month ago