Loading video...

Video Failed to Load

Go Home

This video is at normal speed. Gemma 4 12B MLX version running locally at 50 tokens/sec. Thank you Google DeepMind team. This model feels really solid for a lot of small local tasks and everyday AI workflows.

ai_for_success's profile picture

AshutoshShrivastava

81,073 subscribers

19,843 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

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.
0:40

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

Teamwork makes the dream work. Now running locally. Watch Gemma 4 26B orchestrate 10 parallel sub-agents to code an SVG art gallery in seconds. Hitting 100+ tokens/sec, imagine how you can scale this for complex tasks or local chatbots for entire teams!!
1:30

Teamwork makes the dream work. Now running locally. Watch Gemma 4 26B orchestrate 10 parallel sub-agents to code an SVG art gallery in seconds. Hitting 100+ tokens/sec, imagine how you can scale this for complex tasks or local chatbots for entire teams!!

Google Gemma

158,027 views • 2 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.
2:32

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 • 7 days ago

I’ve been using the new MacBook Pro M5 since launch and it’s a beast, especially compared to my old M1! It’s good for running the smaller AI models locally but also everything you do is just so fast. Here’s Gemma 3 QAT 12B running with MLX:
0:35

I’ve been using the new MacBook Pro M5 since launch and it’s a beast, especially compared to my old M1! It’s good for running the smaller AI models locally but also everything you do is just so fast. Here’s Gemma 3 QAT 12B running with MLX:

Adrien Grondin

101,950 views • 9 months 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. 🙏🏽
1:34

🗓️ 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

I turned the Google Gemma Gemma 4 12B model into an enterprise RFP agent. Running locally in the Hugging Face Llama app and connected to Box, the agent: - pulls the RFP + approved source docs - drafts source-cited responses - flags gaps instead of hallucinating - pauses for human approval - writes the final draft back to Box The model runs locally while Box keeps the enterprise content governed. 00:22 - Demo overview 00:48 - RFP + company sources stored in Box 02:00 - Why local AI works well for confidential document workflows 02:28 - Setting up local AI with the Llama app 04:50 - Walkthrough of AGENTS.md + the script 08:07 - Running the workflow 11:12 - Conclusion
11:30

I turned the Google Gemma Gemma 4 12B model into an enterprise RFP agent. Running locally in the Hugging Face Llama app and connected to Box, the agent: - pulls the RFP + approved source docs - drafts source-cited responses - flags gaps instead of hallucinating - pauses for human approval - writes the final draft back to Box The model runs locally while Box keeps the enterprise content governed. 00:22 - Demo overview 00:48 - RFP + company sources stored in Box 02:00 - Why local AI works well for confidential document workflows 02:28 - Setting up local AI with the Llama app 04:50 - Walkthrough of AGENTS.md + the script 08:07 - Running the workflow 11:12 - Conclusion

Chris Kim

150,387 views • 14 days ago

Gemma 4 is live on Cerebras, the fastest multimodal inference ever! Running on Gemma 4 31B open-weight model at a blistering 1,500+ tokens/sec. That's a 15x speedup, unlocking real-time visual and agentic loops without the GPU lag.
1:33

Gemma 4 is live on Cerebras, the fastest multimodal inference ever! Running on Gemma 4 31B open-weight model at a blistering 1,500+ tokens/sec. That's a 15x speedup, unlocking real-time visual and agentic loops without the GPU lag.

Google Gemma

113,831 views • 1 month ago

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓
0:24

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓

Pau Labarta Bajo

80,258 views • 6 months ago

What can you do with Llama quality and Groq speed? Instant. That's what. 3 months back: Llama 8B running at 750 Tokens/sec Now: Llama 70B model running at 3,200 Tokens/sec We're still going to get a liiiiiiitle bit faster, but this is our V1 14nm LPU - how fast will V2 be? 😉
0:39

What can you do with Llama quality and Groq speed? Instant. That's what. 3 months back: Llama 8B running at 750 Tokens/sec Now: Llama 70B model running at 3,200 Tokens/sec We're still going to get a liiiiiiitle bit faster, but this is our V1 14nm LPU - how fast will V2 be? 😉

Jonathan Ross

179,815 views • 1 year ago

the era of agentic AI is here Google just open sourced Gemma 3, you can run it on a single GPU laptop or even phone - agentic AI workflows - 4 Sizes – 1B, 4B, 12B, 27B - up to 128K tokens - speaks 140+ languages - hit 1338 ELO on LMArena try & download for free, links 👇
3:56

the era of agentic AI is here Google just open sourced Gemma 3, you can run it on a single GPU laptop or even phone - agentic AI workflows - 4 Sizes – 1B, 4B, 12B, 27B - up to 128K tokens - speaks 140+ languages - hit 1338 ELO on LMArena try & download for free, links 👇

el.cine

199,546 views • 1 year ago

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:
2:08

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:

Cerebras

282,043 views • 2 months ago

🔴 The Pain: Running local MLX models is incredibly fast and private. But let's be real - testing tool calling via terminal is clunky, and there's zero good UI for it. 🟢 The Fix: rapid-mlx share Just ONE command gives you a polished web chat + seamless tool calling (works beautifully with gemma-4-12b-qat). We are proud to be the ONLY MLX inference engine in the community shipping this. ⚡️ 👇 Try it now: brew install raullenchai/rapid-mlx/rapid-mlx
0:40

🔴 The Pain: Running local MLX models is incredibly fast and private. But let's be real - testing tool calling via terminal is clunky, and there's zero good UI for it. 🟢 The Fix: rapid-mlx share Just ONE command gives you a polished web chat + seamless tool calling (works beautifully with gemma-4-12b-qat). We are proud to be the ONLY MLX inference engine in the community shipping this. ⚡️ 👇 Try it now: brew install raullenchai/rapid-mlx/rapid-mlx

raullen

22,760 views • 2 months ago

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.
1:36

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

BridgeMind

70,626 views • 2 months ago

This is all you need for running Deepseek R1 671B at home. Her the model with Q4 running on a $2000 Local Machine - 3.5 to 4 tokens per second. 512GB DDR4 RAM Video from "Digital Spaceport" YT Channel (link in comment)
0:59

This is all you need for running Deepseek R1 671B at home. Her the model with Q4 running on a $2000 Local Machine - 3.5 to 4 tokens per second. 512GB DDR4 RAM Video from "Digital Spaceport" YT Channel (link in comment)

Rohan Paul

312,049 views • 1 year ago

You can run Google new Gemma 4 on mobile easily. I am using Gemma 4 version E2B on my Pixel 10 Pro. Here is all you need to do: - Go to the App Store and install Google AI Edge Gallery. If you already have it, just update it. - From there, you can install the model directly and start using it. Still exploring what this small but powerful model can do :)
1:28

You can run Google new Gemma 4 on mobile easily. I am using Gemma 4 version E2B on my Pixel 10 Pro. Here is all you need to do: - Go to the App Store and install Google AI Edge Gallery. If you already have it, just update it. - From there, you can install the model directly and start using it. Still exploring what this small but powerful model can do :)

AshutoshShrivastava

226,599 views • 5 months ago

At Google I/O, I sat down with Omar Sanseviero and 👩‍💻 Paige Bailey from Google DeepMind to talk about Gemma, open models, AI Studio, on-device AI, sovereign AI and the future of AI development. A great conversation on how building with AI is becoming more open, local and accessible.
26:51

At Google I/O, I sat down with Omar Sanseviero and 👩‍💻 Paige Bailey from Google DeepMind to talk about Gemma, open models, AI Studio, on-device AI, sovereign AI and the future of AI development. A great conversation on how building with AI is becoming more open, local and accessible.

Chubby♨️

13,741 views • 3 months ago

this dude created a Gemma 4 that is 6X faster than Google's version! Gemma 4 is notorious for: • being the most optimized free open source local AI • that works with even old laptops and smartphones • and now it's insanely fast 6X Dflash Gemma 4:
0:26

this dude created a Gemma 4 that is 6X faster than Google's version! Gemma 4 is notorious for: • being the most optimized free open source local AI • that works with even old laptops and smartphones • and now it's insanely fast 6X Dflash Gemma 4:

Meta Alchemist

278,341 views • 3 months ago

what is a multimodal LLM thinking as it watches a video? Gemma 4 12B reads raw image patches, as if they were tokens. It was never trained to predict anything at these 'tokens' - but this video shows what it would predict if you did sample from its next token prediction head
0:53

what is a multimodal LLM thinking as it watches a video? Gemma 4 12B reads raw image patches, as if they were tokens. It was never trained to predict anything at these 'tokens' - but this video shows what it would predict if you did sample from its next token prediction head

Matt Henderson

163,504 views • 1 month ago

Few seconds and <4GB to full fine tune Gemma 3 270M for classification tasks! Here on M3 Ultra! I'll keep experimenting and checking final result! base model, batch size 4, adaw (testing with adafactor too!), rank 128. Video at normal speed here! 🔥
0:35

Few seconds and <4GB to full fine tune Gemma 3 270M for classification tasks! Here on M3 Ultra! I'll keep experimenting and checking final result! base model, batch size 4, adaw (testing with adafactor too!), rank 128. Video at normal speed here! 🔥

Ivan Fioravanti ᯅ

35,282 views • 1 year ago

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.
1:15

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.

Aditya ⚡Rao

85,060 views • 2 months ago