Loading video...

Video Failed to Load

Go Home

Gemma 4 12B dropped today. Apache 2.0, multimodal: text, image, audio, and video. 256K context, built-in thinking, native tool calling. Running on Red Hat OpenShift AI with vLLM on Day 0:

RedHat_AI's profile picture

Red Hat AI

11,827 subscribers

15,995 views • 2 months ago •via X (Twitter)

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 Gemma 4, their most capable open models yet! 🤯 Apache-2.0, multimodal (text, image, and audio input), and multilingual (140 languages)! They can even run 100% locally in your browser on WebGPU. Watch it describe the Artemis II launch! 🚀 Try the demo! 👇
1:35

NEW: Google releases Gemma 4, their most capable open models yet! 🤯 Apache-2.0, multimodal (text, image, and audio input), and multilingual (140 languages)! They can even run 100% locally in your browser on WebGPU. Watch it describe the Artemis II launch! 🚀 Try the demo! 👇

Xenova

38,427 views • 4 months ago

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it!
1:39

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it!

Omar Sanseviero

125,574 views • 2 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.
2:51

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

1,669,786 views • 4 months ago

Unlock local, agentic workflows with Gemma 4 12B and Google AI Edge, directly on your laptop. Experience 100% on-device AI: • Generate code in AI Edge Gallery (new to Mac) • Dictate and edit text via AI Edge Eloquent (new to Mac) • Serve Gemma 4 12B locally with LiteRT-LM Dive in:
1:40

Unlock local, agentic workflows with Gemma 4 12B and Google AI Edge, directly on your laptop. Experience 100% on-device AI: • Generate code in AI Edge Gallery (new to Mac) • Dictate and edit text via AI Edge Eloquent (new to Mac) • Serve Gemma 4 12B locally with LiteRT-LM Dive in:

Google for Developers

140,169 views • 2 months ago

The wait is over 💥 Seedance 2.0 is now on Freepik. EVERY plan. EVERYWHERE → Full cinematic video from a SINGLE prompt → Multimodal: text, image, video, audio → Lip-sync and beat-synced audio built in → Motion control via references Try it now on Freepik
0:28

The wait is over 💥 Seedance 2.0 is now on Freepik. EVERY plan. EVERYWHERE → Full cinematic video from a SINGLE prompt → Multimodal: text, image, video, audio → Lip-sync and beat-synced audio built in → Motion control via references Try it now on Freepik

Magnific

133,584 views • 3 months ago

Step-3.7-Flash Q4_K_S on DGX Spark (GB10, 128GB): > ~27 tok/s generation > 198B sparse MoE, ~11B active > 256K context, native vision > Agentic / tool-calling / reasoning > Apache 2.0 I added a mobile chat screen on the right showing what 27 tok/s actually feels like streaming on a phone.
0:52

Step-3.7-Flash Q4_K_S on DGX Spark (GB10, 128GB): > ~27 tok/s generation > 198B sparse MoE, ~11B active > 256K context, native vision > Agentic / tool-calling / reasoning > Apache 2.0 I added a mobile chat screen on the right showing what 27 tok/s actually feels like streaming on a phone.

stevibe

19,658 views • 2 months ago

watch gemma 4 12b q8 dancing on a single rtx 3090 at 33 tokens a second average. google dropped this two days ago and it's the kind of thing that quietly moves the floor. a fully multimodal model, text image and audio in one net, 256k context, apache licensed, running entirely on one consumer gpu, no one metering your tokens. what you're watching is the whole loop live: the server streaming tokens top left, the gpu pegged bottom left, the answer landing on the right. all local, all mine. a year ago this needed someone else's datacenter. today it's a card you can buy. open source isn't catching up anymore, it's setting the pace. how fast does yours run?
0:34

watch gemma 4 12b q8 dancing on a single rtx 3090 at 33 tokens a second average. google dropped this two days ago and it's the kind of thing that quietly moves the floor. a fully multimodal model, text image and audio in one net, 256k context, apache licensed, running entirely on one consumer gpu, no one metering your tokens. what you're watching is the whole loop live: the server streaming tokens top left, the gpu pegged bottom left, the answer landing on the right. all local, all mine. a year ago this needed someone else's datacenter. today it's a card you can buy. open source isn't catching up anymore, it's setting the pace. how fast does yours run?

Sudo su

36,614 views • 2 months ago

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below
0:36

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

Paul Couvert

725,944 views • 4 months ago

Gemini 3.1 Flash Live just dropped and it's available with LiveKit today. This is the first Gemini 3 native audio model on the Live API. Better instruction following, improved tool calling, reduced speaker drift, and support for 70+ languages. Audio in, audio out. No text conversion in between.
1:23

Gemini 3.1 Flash Live just dropped and it's available with LiveKit today. This is the first Gemini 3 native audio model on the Live API. Better instruction following, improved tool calling, reduced speaker drift, and support for 70+ languages. Audio in, audio out. No text conversion in between.

LiveKit

40,277 views • 4 months ago

📲 Gemma 3n delivers advanced on-device AI with optimized performance and multimodal understanding. Take a closer look at the early preview text capabilities available in Google AI Studio, GenAI SDK, and text/image capabilities via MediaPipe.
5:47

📲 Gemma 3n delivers advanced on-device AI with optimized performance and multimodal understanding. Take a closer look at the early preview text capabilities available in Google AI Studio, GenAI SDK, and text/image capabilities via MediaPipe.

Google AI Developers

16,639 views • 1 year ago

KLING O3 JUST LANDED IN HEDRA – DAY 0 🔥 Unified multimodal monster: 15s videos, native audio baked in, 10+ refs, text/image/video-to-video, insane consistency & creative control. Hedra got it first. You got it now.
0:44

KLING O3 JUST LANDED IN HEDRA – DAY 0 🔥 Unified multimodal monster: 15s videos, native audio baked in, 10+ refs, text/image/video-to-video, insane consistency & creative control. Hedra got it first. You got it now.

Hedra

12,375 views • 6 months ago

🚨 It is here! Kling 2.6 is launching exclusively on fal day 0! 🎬 Native audio generation for text-to-video and image-to-video 🎵 Cinematic storytelling with expressive audio performances ✨ High-intensity VFX with detailed sound design
2:28

🚨 It is here! Kling 2.6 is launching exclusively on fal day 0! 🎬 Native audio generation for text-to-video and image-to-video 🎵 Cinematic storytelling with expressive audio performances ✨ High-intensity VFX with detailed sound design

fal

81,095 views • 8 months ago

MiniMax H3 is now live on Topview 🔥 We’re excited to partner with Hailuo AI (MiniMax) MiniMax (official) to bring MiniMax H3 to creators. Native 2K, 15s clips, and stronger multimodal control across text, image, audio, and video. Only 30% of Seedance 2.0’s price. Ultra Annual users get 60 days unlimited.
0:40

MiniMax H3 is now live on Topview 🔥 We’re excited to partner with Hailuo AI (MiniMax) MiniMax (official) to bring MiniMax H3 to creators. Native 2K, 15s clips, and stronger multimodal control across text, image, audio, and video. Only 30% of Seedance 2.0’s price. Ultra Annual users get 60 days unlimited.

TopviewAI

1,467,396 views • 7 days ago

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗
0:21

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

vLLM

40,306 views • 1 month ago

Google has been cooking in recent days: → 2.0 Flash native image gen → Data analysis agent in Colab → Gemma 3 open source models → YT video multimodal understanding → Gemini with Search history → Deep Research 2.0 → AI Mode in Search All this in less than 10 days 🔥
0:37

Google has been cooking in recent days: → 2.0 Flash native image gen → Data analysis agent in Colab → Gemma 3 open source models → YT video multimodal understanding → Gemini with Search history → Deep Research 2.0 → AI Mode in Search All this in less than 10 days 🔥

Paul Couvert

25,653 views • 1 year ago

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal. The highlights: → Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it → VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported → Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1 Learn more with our blog 👇
0:47

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal. The highlights: → Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it → VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported → Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1 Learn more with our blog 👇

ComfyUI

20,064 views • 2 months ago

Gemma 4 Diffusion landed in vLLM last week. Day 0. First diffusion LLM natively supported in vLLM. Instead of one token at a time, it predicts 256 tokens at once and iteratively denoises them in parallel. Result: 1,000+ tokens per second at batch size 1 on a single H100. Built on Model Runner V2. Google Gemma
1:56

Gemma 4 Diffusion landed in vLLM last week. Day 0. First diffusion LLM natively supported in vLLM. Instead of one token at a time, it predicts 256 tokens at once and iteratively denoises them in parallel. Result: 1,000+ tokens per second at batch size 1 on a single H100. Built on Model Runner V2. Google Gemma

Red Hat AI

17,637 views • 1 month ago

Today we announced Gemini 2.0, our most capable AI model yet. With new advances in multimodality — like native image and audio output — and native tool use, it will enable us to build new AI agents that bring us closer to our vision of a universal assistant.
2:52

Today we announced Gemini 2.0, our most capable AI model yet. With new advances in multimodality — like native image and audio output — and native tool use, it will enable us to build new AI agents that bring us closer to our vision of a universal assistant.

Google

137,190 views • 1 year ago

Next mlx-vlm release will ship with continuous batching support on the server 🚀 What's coming: → Continuous batching — new requests join the active batch immediately, no waiting. Mixed image + text batches supported → OpenAI-compatible API — field-for-field match with mlx-lm, reasoning/content split for thinking models, tag-aware streaming → Multi-turn tool calling — full tool use support across streaming and non-streaming, works with Gemma4 and other templates → Vision feature caching — cache image embeddings across turns. Gemma4: 228x speedup, Qwen3.5: 23x on cache hit All running locally on Apple Silicon. Check our this demo running 4 concurrent requests (mixed image + text) to gemma-4-26B-A4B-IT by Google Gemma in bf16 using Pi + MLX-VLM server on my M3 Ultra. One of the requests ingests a 8K resolution image!
0:52

Next mlx-vlm release will ship with continuous batching support on the server 🚀 What's coming: → Continuous batching — new requests join the active batch immediately, no waiting. Mixed image + text batches supported → OpenAI-compatible API — field-for-field match with mlx-lm, reasoning/content split for thinking models, tag-aware streaming → Multi-turn tool calling — full tool use support across streaming and non-streaming, works with Gemma4 and other templates → Vision feature caching — cache image embeddings across turns. Gemma4: 228x speedup, Qwen3.5: 23x on cache hit All running locally on Apple Silicon. Check our this demo running 4 concurrent requests (mixed image + text) to gemma-4-26B-A4B-IT by Google Gemma in bf16 using Pi + MLX-VLM server on my M3 Ultra. One of the requests ingests a 8K resolution image!

Prince Canuma

82,169 views • 3 months ago

Seedance 2.0 Mini is now live on Venice. ByteDance's fastest video model. Text-to-video, image-to-video, and reference-to-video with native audio. Up to 15s at 720p. Available to all users, anonymously
0:33

Seedance 2.0 Mini is now live on Venice. ByteDance's fastest video model. Text-to-video, image-to-video, and reference-to-video with native audio. Up to 15s at 720p. Available to all users, anonymously

Venice

14,196 views • 1 month ago