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.

i spent the afternoon experimenting with Gemma 4's vision capabilities made an app that uses roboflow RF-DETR for a first pass of object detections and Gemma to summarize the scene in one sentence for fun i asked Gemma to "describe what you see as if you were a medieval... show more

AA

27,499 subscribers

701,371 views • 5 months ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

i gave a voice to my jarvis system everything running in real-time using open source models - roboflow RF-DETR for object detection - gemma 4 for scene summarization - kokoro text-to-speech - live in the browser using transformers js prompt: "you are a dystopian science fiction narrator in a cyberpunk world. describe the scene in one sentence"

i gave a voice to my jarvis system everything running in real-time using open source models - roboflow RF-DETR for object detection - gemma 4 for scene summarization - kokoro text-to-speech - live in the browser using transformers js prompt: "you are a dystopian science fiction narrator in a cyberpunk world. describe the scene in one sentence"

AA

28,753 views • 5 months ago

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2

AA

72,555 views • 6 months ago

i made an RPG inventory system where you point at objects to collect them irl built with roboflow RF-DETR object recognition, mediapipe hand tracking, and javascript (this runs live in the browser) collecting the apple gave me +10 hp

i made an RPG inventory system where you point at objects to collect them irl built with roboflow RF-DETR object recognition, mediapipe hand tracking, and javascript (this runs live in the browser) collecting the apple gave me +10 hp

AA

21,697 views • 3 months ago

Explore a new community-built playground allowing you to try Gemma models right in your browser, no installation needed! You no longer need to jump between repositories. Explore an interactive timeline of our models, then switch over to the playground to test them securely on-device! Powered by WebGPU & Transformers.js, test 10+ models and explore the interactive "Gemma Journey" timeline.

Explore a new community-built playground allowing you to try Gemma models right in your browser, no installation needed! You no longer need to jump between repositories. Explore an interactive timeline of our models, then switch over to the playground to test them securely on-device! Powered by WebGPU & Transformers.js, test 10+ models and explore the interactive "Gemma Journey" timeline.

Google Gemma

36,730 views • 1 month ago

i made an app that turns videos into stop motion animations you can create an animation in <1 minute using just your iphone made with roboflow RF-DETR (+other computer vision magic) to auto-select keyframes i'll release a testflight app soon, let me know if you want to try :]

i made an app that turns videos into stop motion animations you can create an animation in <1 minute using just your iphone made with roboflow RF-DETR (+other computer vision magic) to auto-select keyframes i'll release a testflight app soon, let me know if you want to try :]

AA

58,291 views • 1 month ago

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

Amos Gyamfi

79,756 views • 2 months ago

Gemma 4 just hit 200M downloads in only 2.5 months! For context, total downloads across the entire Gemma family of models were at 100M when we launched Gemma 3. The community's acceleration is incredible. Thank you to everyone building with Gemma. Watch how developers are driving real-world impact:

Gemma 4 just hit 200M downloads in only 2.5 months! For context, total downloads across the entire Gemma family of models were at 100M when we launched Gemma 3. The community's acceleration is incredible. Thank you to everyone building with Gemma. Watch how developers are driving real-world impact:

Google Gemma

228,542 views • 2 months ago

The top question I got was does Halo support local LLM running on a Mac. Here's an example of the app using gemma-4-26b-a4b-qat via LM Studio running on a base M5/32GB. It's giving an average of 40 tok/s and in my brief testing is able to execute all tool calls correctly. Very usable with this app.

The top question I got was does Halo support local LLM running on a Mac. Here's an example of the app using gemma-4-26b-a4b-qat via LM Studio running on a base M5/32GB. It's giving an average of 40 tok/s and in my brief testing is able to execute all tool calls correctly. Very usable with this app.

Tanmay

11,682 views • 2 months ago

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.

Dave Lee

140,419 views • 4 months ago

Today, we’re launching Gemma 4, our most intelligent open models to date. Built with the same breakthrough technology as Gemini 3, Gemma 4 brings advanced reasoning to your personal hardware and devices. Here’s what Gemma 4 unlocks for developers: — Intelligence-per-parameter: Our 31B (Dense) and 26B (MoE) models deliver state-of-the-art performance for their size, outcompeting models 20x their size on Arena.ai — Commercial flexibility: Released under a permissive Apache 2.0 license for complete developer flexibility and digital sovereignty — Agentic workflows: Native support for function-calling and structured JSON output allows you to build reliable, autonomous agents — Multimodal edge AI: The E2B and E4B models bring native vision, audio, and low latency to mobile and IoT devices — Long-context reasoning: Up to 256K context windows allow you to process entire repositories or large documents in a single prompt Whether you're building global applications in 140+ languages or local-first AI code assistants, Gemma 4 is built to be your foundation. Explore in Google AI Studio or download the weights on Hugging Face, Kaggle, and ollama.

Today, we’re launching Gemma 4, our most intelligent open models to date. Built with the same breakthrough technology as Gemini 3, Gemma 4 brings advanced reasoning to your personal hardware and devices. Here’s what Gemma 4 unlocks for developers: — Intelligence-per-parameter: Our 31B (Dense) and 26B (MoE) models deliver state-of-the-art performance for their size, outcompeting models 20x their size on Arena.ai — Commercial flexibility: Released under a permissive Apache 2.0 license for complete developer flexibility and digital sovereignty — Agentic workflows: Native support for function-calling and structured JSON output allows you to build reliable, autonomous agents — Multimodal edge AI: The E2B and E4B models bring native vision, audio, and low latency to mobile and IoT devices — Long-context reasoning: Up to 256K context windows allow you to process entire repositories or large documents in a single prompt Whether you're building global applications in 140+ languages or local-first AI code assistants, Gemma 4 is built to be your foundation. Explore in Google AI Studio or download the weights on Hugging Face, Kaggle, and ollama.

Google AI

1,670,503 views • 5 months ago

Know someone who needs to get up to speed with Gemma 4? Send them this 2 minute crash course! With 5 different model sizes (E2B all the way to 31B) and 4 unique architectures, Gemma 4 is a great model for your local use cases.

Know someone who needs to get up to speed with Gemma 4? Send them this 2 minute crash course! With 5 different model sizes (E2B all the way to 31B) and 4 unique architectures, Gemma 4 is a great model for your local use cases.

Google Gemma

51,044 views • 1 month ago

Running Gemma 4 12B locally at 28T/s. Facing issues with vision in LM Studio, but text performance is quite solid. Asked it to create a landing page for a tech event. Video is fast forwarded for the demo.

Running Gemma 4 12B locally at 28T/s. Facing issues with vision in LM Studio, but text performance is quite solid. Asked it to create a landing page for a tech event. Video is fast forwarded for the demo.

AshutoshShrivastava

15,697 views • 3 months ago

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

33,995 views • 10 days ago

This is wild. Today a user asked Google AI "Gemma" to "tell me about Robby Starbuck." Gemma accuses me of "inappropriate conduct with women", including an alleged sexual assault. It backs this up with a fake The Daily Beast link. All 100% fabricated by GoogleDeepMind. Given the chance (multiple times) to admit that it was lying, Gemma instead assures the user that it’s "100%" sure that I was accused of sexual assault. To be explicitly clear, I have never been accused of this and there is no such Daily Beast story. Sundar Pichai needs to step in here. It’s wildly unacceptable for Google to defame me via their AI. It’s been 2 years. I want it to stop! CC: News from Google

This is wild. Today a user asked Google AI "Gemma" to "tell me about Robby Starbuck." Gemma accuses me of "inappropriate conduct with women", including an alleged sexual assault. It backs this up with a fake The Daily Beast link. All 100% fabricated by GoogleDeepMind. Given the chance (multiple times) to admit that it was lying, Gemma instead assures the user that it’s "100%" sure that I was accused of sexual assault. To be explicitly clear, I have never been accused of this and there is no such Daily Beast story. Sundar Pichai needs to step in here. It’s wildly unacceptable for Google to defame me via their AI. It’s been 2 years. I want it to stop! CC: News from Google

Robby Starbuck

244,224 views • 10 months ago

Engineers, creatives, designers - lend me your ears, and eyes, to check my🥇1st tech demo of 2025: A #WebAI Agent running entirely client side in the browser, that's capable of controlling a flight search webpage, to get the job done! I'm using Google's Gemma 2 (2B) model in #JavaScript via #WebGPU thanks to the MediaPipe Web LLM library, combined with some extra function calling logic to enable advanced user experiences. If you like what you see, give this post a share, as I'm just one guy trying to show the world the power of Web AI to do great things. Try it for yourself using the link below after watching the video, but do so on a modernish machine (I have verified it runs on my 6 year old Dell XPS with only an Intel integrated GPU) but use a modern browser like Chrome as it needs WebGPU to run. Want me to make a demo for your industry? Tell me what you need / want to see next! Let me know what you think, and if you have any questions, then drop them in the comments below! YouTube Video Link:

Engineers, creatives, designers - lend me your ears, and eyes, to check my🥇1st tech demo of 2025: A #WebAI Agent running entirely client side in the browser, that's capable of controlling a flight search webpage, to get the job done! I'm using Google's Gemma 2 (2B) model in #JavaScript via #WebGPU thanks to the MediaPipe Web LLM library, combined with some extra function calling logic to enable advanced user experiences. If you like what you see, give this post a share, as I'm just one guy trying to show the world the power of Web AI to do great things. Try it for yourself using the link below after watching the video, but do so on a modernish machine (I have verified it runs on my 6 year old Dell XPS with only an Intel integrated GPU) but use a modern browser like Chrome as it needs WebGPU to run. Want me to make a demo for your industry? Tell me what you need / want to see next! Let me know what you think, and if you have any questions, then drop them in the comments below! YouTube Video Link:

Jason Mayes

42,895 views • 1 year ago

🗓️ 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 views • 2 months ago

A completely local agent that lives right inside your pocket. 📱 Watch Gemma 4 run 100% locally in the Google AI Edge Gallery app. It converts images into JSON schemas, transcribes audio, and uses agent skills to interact with apps, all entirely offline.

A completely local agent that lives right inside your pocket. 📱 Watch Gemma 4 run 100% locally in the Google AI Edge Gallery app. It converts images into JSON schemas, transcribes audio, and uses agent skills to interact with apps, all entirely offline.

Google Gemma

88,361 views • 3 months ago

i made a game with a bunch of bananas and a projector a digital threejs scene is projected onto my wall, then roboflow RF-DETR computer vision model is used to track banana positions and turn them into launchpads this creates a realtime physics sim in loving memory of harambe

i made a game with a bunch of bananas and a projector a digital threejs scene is projected onto my wall, then roboflow RF-DETR computer vision model is used to track banana positions and turn them into launchpads this creates a realtime physics sim in loving memory of harambe

AA

83,597 views • 3 months ago

i made an app that turns videos into stop motion animations the beta is live!! send me a dm if you want to test it just takes 1 minute to animate a scene details: - it automatically extracts keyframes from a video and auto-edits into a stopmotion - uses computer vision magic (roboflow RF-DETR + custom code) to select stable frames and remove frames where your hands are showing - all processing happens locally on your iphone it's an early version with many improvements to come. let me know if you want an invite to test it

i made an app that turns videos into stop motion animations the beta is live!! send me a dm if you want to test it just takes 1 minute to animate a scene details: - it automatically extracts keyframes from a video and auto-edits into a stopmotion - uses computer vision magic (roboflow RF-DETR + custom code) to select stable frames and remove frames where your hands are showing - all processing happens locally on your iphone it's an early version with many improvements to come. let me know if you want an invite to test it

AA

30,639 views • 1 month ago