Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Looking for a better local model that runs on a MacBook Air? Our latest update brings full Gemma 4 12B support to Google AI Edge Gallery app on Mac. ✨ Multimodal: Vision & Audio inputs 🎛️ Configurable vision token budgets ⚡️ MTP for blazing-fast inference 💻 Optimized to run...

googlegemma's profile picture

Google Gemma

98,960 subscribers

115,597 Aufrufe • vor 5 Tagen •via X (Twitter)

BildungGesundheit & WellnessWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

16 Kommentare

Profilbild von Google Gemma
Google Gemmavor 5 Tagen

Access the updated Gemma 4 12B file: Quickly try Gemma using LiteRT-LM CLI: Learn more about building with LiteRT-LM:

Profilbild von Hussain Hashim | Building SundayBack
Hussain Hashim | Building SundayBackvor 5 Tagen

@googlegemma that's cool, I struggled with local models on my MacBook Air. Excited to see how this setup improves speed and performance!

Profilbild von okimraise.eth
okimraise.ethvor 5 Tagen

nice that 12b landed on a 16gb air with vision and audio in the same app the vision token budget is the knob people will actually twist first

Profilbild von Chen
Chenvor 5 Tagen

model was fine. nobody had a reason to open it again

Profilbild von FuturePaddy
FuturePaddyvor 5 Tagen

Running Gemma 12B on my MacBook Pro. It’s doing a great job at what I’m using it for. 🙏

Profilbild von Achu Mukundan
Achu Mukundanvor 5 Tagen

neat!

Profilbild von Steve • Plus
Steve • Plusvor 5 Tagen

Hallu cin at ions!

Profilbild von Antoine Ríos ッ
Antoine Ríos ッvor 5 Tagen

No. Does not work comflrtably too tight

Profilbild von Roenel
Roenelvor 5 Tagen

Gemma 5, please be better than qwen 3.8

Profilbild von ライトサン
ライトサンvor 5 Tagen

Gemma 5 20B dense model?

Profilbild von airplanestar 𓂀
airplanestar 𓂀vor 5 Tagen

optimizing on-device token budgets for local multi-modal inference changes the efficiency curve completely for portable hardware runs

Profilbild von ShipNomad
ShipNomadvor 5 Tagen

Can the vision budget change per image? I'd try a higher setting for a screenshot with tiny text without using it for every photo.

Profilbild von furomoad
furomoadvor 5 Tagen

Bro plz release Gemma 5

Profilbild von AIBotics
AIBoticsvor 5 Tagen

Processing vision inputs completely locally without sending everything to a server is exactly why having Apple silicon is actually worth it now.

Profilbild von ZX Huang
ZX Huangvor 4 Tagen

Why do people like to make their own harnesses?

Profilbild von AI Mastery Guide
AI Mastery Guidevor 4 Tagen

running local on a macbook air, nice

Ähnliche Videos

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.
0:20

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.

Google AI Developers

125,331 Aufrufe • vor 1 Jahr

🗓️ 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 Aufrufe • vor 3 Monaten

to run gemma 4 on your phone without any login or internet: - download Google AI Edge Gallery - select Gemma 4 E2B/E4B - thats it I wish they give support to add other edge models in future like locallyAI here is a video of gemma 4 E4B in action at 13 tps on iphone 15 pro max
2:55

to run gemma 4 on your phone without any login or internet: - download Google AI Edge Gallery - select Gemma 4 E2B/E4B - thats it I wish they give support to add other edge models in future like locallyAI here is a video of gemma 4 E4B in action at 13 tps on iphone 15 pro max

Harveen Singh Chadha

13,588 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 3 Monaten

GEMMA 4 IS STARTING TO KILL A LOT OF AI SUBSCRIPTIONS. Local inference, multimodal support, strong coding, and no API bill is making “just run it on your own machine” feel way more real.
9:24

GEMMA 4 IS STARTING TO KILL A LOT OF AI SUBSCRIPTIONS. Local inference, multimodal support, strong coding, and no API bill is making “just run it on your own machine” feel way more real.

0xMarioNawfal

65,679 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 5 Monaten

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.
3:20

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

88,541 Aufrufe • vor 3 Monaten

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

85,093 Aufrufe • vor 3 Monaten

Run OpenClaw 2.0 through Atomic Chat local LLM server on a 16GB MacBook 💻🦞 We gave OpenClaw a task to edit a video using Gemma 4 E4B, it successfully created a welcome video in two minutes by writing custom React code Load the model in start the LLM server and OpenClaw 2.0 picks it right up
0:27

Run OpenClaw 2.0 through Atomic Chat local LLM server on a 16GB MacBook 💻🦞 We gave OpenClaw a task to edit a video using Gemma 4 E4B, it successfully created a welcome video in two minutes by writing custom React code Load the model in start the LLM server and OpenClaw 2.0 picks it right up

atomic.chat

44,413 Aufrufe • vor 20 Tagen

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

1,670,724 Aufrufe • vor 5 Monaten

Gemma 4 12B QAT + MTP on 8GB VRAM. llama.cpp flags included. let's run it. 20+ tok/sec decode. 700+ tok/sec prefill. on a single RTX 4060. copy these exact flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf \ --spec-type draft-mtp \ --spec-draft-n-max 4 \ --spec-draft-p-min 0.7 \ --spec-draft-model gemma-4-12B-it-qat-assistant-MTP-Q8_0.gguf \ -c 48000 -ngl 38 -v → -ngl 99 if you're on 12–24GB VRAM (RTX 3090, 4090, 4080, 3080, 4070 Ti, 3080 Ti) → -ngl 38 for 8GB setups with 48k context (RTX 4060, 3060, 2080, 2070, 3070) → drop it (or the context) lower if you're squeezing on 4–6GB (RTX 2060, 3050, 1660) my rig: RTX 4060 8GB · i7H · 16GB RAM MTP is giving me 25–40% decode throughput gains across Gemma 4 models. nearly zero VRAM cost for that bump. the draft assistant GGUF is only ~300–400MB depending on quant. one thing to know (architectural catch): unlike Qwen3.6 and Qwen3.5 models which bakes MTP heads straight into the base GGUF, Gemma 4 needs a separate draft assistant model downloaded alongside. not a big deal. just don't forget it or MTP won't run. draft assistant GGUF link → comments while you wait for anthropic mythos release, test this and drop your decode numbers below, curious how it scales across different setups.
0:21

Gemma 4 12B QAT + MTP on 8GB VRAM. llama.cpp flags included. let's run it. 20+ tok/sec decode. 700+ tok/sec prefill. on a single RTX 4060. copy these exact flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf \ --spec-type draft-mtp \ --spec-draft-n-max 4 \ --spec-draft-p-min 0.7 \ --spec-draft-model gemma-4-12B-it-qat-assistant-MTP-Q8_0.gguf \ -c 48000 -ngl 38 -v → -ngl 99 if you're on 12–24GB VRAM (RTX 3090, 4090, 4080, 3080, 4070 Ti, 3080 Ti) → -ngl 38 for 8GB setups with 48k context (RTX 4060, 3060, 2080, 2070, 3070) → drop it (or the context) lower if you're squeezing on 4–6GB (RTX 2060, 3050, 1660) my rig: RTX 4060 8GB · i7H · 16GB RAM MTP is giving me 25–40% decode throughput gains across Gemma 4 models. nearly zero VRAM cost for that bump. the draft assistant GGUF is only ~300–400MB depending on quant. one thing to know (architectural catch): unlike Qwen3.6 and Qwen3.5 models which bakes MTP heads straight into the base GGUF, Gemma 4 needs a separate draft assistant model downloaded alongside. not a big deal. just don't forget it or MTP won't run. draft assistant GGUF link → comments while you wait for anthropic mythos release, test this and drop your decode numbers below, curious how it scales across different setups.

Alok

29,006 Aufrufe • vor 3 Monaten

Gemma 4 can run on phones without an internet connection! 🤯 It can perform local agentic tasks, such as logging and analyzing trends. When connected, it can also make API calls. Want to try it yourself? Get the Google AI Edge App on iOS or Android. (🔊 Sound on for the demo!)
2:44

Gemma 4 can run on phones without an internet connection! 🤯 It can perform local agentic tasks, such as logging and analyzing trends. When connected, it can also make API calls. Want to try it yourself? Get the Google AI Edge App on iOS or Android. (🔊 Sound on for the demo!)

Google Gemma

760,219 Aufrufe • vor 5 Monaten

WHY IS NO ONE TALKING ABOUT THIS?? Gemma 3n model was one of the best surprises for me. The fact that you can run it on edge devices even with just 2GB of RAM is impressive. A few weeks back, I was on holiday and used the Gemini Live feature a lot. But I kept running into issues whenever I was in a place where the network wasn’t reliable. Gemma 3n : > Multimodal: Supports text and image inputs; video/audio in development. > Context Window: Up to 128K tokens (32K for 1B model). > Multilingual: Trained on 140+ languages. > Privacy: Offline, on-device processing for data security. > Model Sizes: E2B (5B parameters, 2GB RAM) and E4B (10–12B parameters, 3GB RAM). Video credit: Google YT
1:34

WHY IS NO ONE TALKING ABOUT THIS?? Gemma 3n model was one of the best surprises for me. The fact that you can run it on edge devices even with just 2GB of RAM is impressive. A few weeks back, I was on holiday and used the Gemini Live feature a lot. But I kept running into issues whenever I was in a place where the network wasn’t reliable. Gemma 3n : > Multimodal: Supports text and image inputs; video/audio in development. > Context Window: Up to 128K tokens (32K for 1B model). > Multilingual: Trained on 140+ languages. > Privacy: Offline, on-device processing for data security. > Model Sizes: E2B (5B parameters, 2GB RAM) and E4B (10–12B parameters, 3GB RAM). Video credit: Google YT

AshutoshShrivastava

210,641 Aufrufe • vor 1 Jahr

The Gemma family continues to grow today! 🩺 Announcing new models for MedGemma, our collection of multimodal open models specifically designed for health AI development that can run on a single GPU. 1️⃣ MedGemma 27B Multimodal 2️⃣ MedSigLIP (Read the thread to learn more)
0:56

The Gemma family continues to grow today! 🩺 Announcing new models for MedGemma, our collection of multimodal open models specifically designed for health AI development that can run on a single GPU. 1️⃣ MedGemma 27B Multimodal 2️⃣ MedSigLIP (Read the thread to learn more)

Google AI Developers

61,037 Aufrufe • vor 1 Jahr

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

199,579 Aufrufe • vor 1 Jahr

Introducing hybrid compute in Perplexity Computer. Computer can start a task in the cloud, then move to a local model that runs on your Mac. Use it for steps involving private files or sensitive data. Available today in the Perplexity Mac app.
1:08

Introducing hybrid compute in Perplexity Computer. Computer can start a task in the cloud, then move to a local model that runs on your Mac. Use it for steps involving private files or sensitive data. Available today in the Perplexity Mac app.

Perplexity

286,221 Aufrufe • vor 20 Tagen

PERPLEXITY 🔥: A new Hybrid mode is coming soon on Mac, letting local models handle some subtasks. > Gemma 4 (for 16 GB machines), Qwen3.6, and Perplexity's own model (For 32 GB machines) are currently supported. > "In Hybrid mode, Computer orchestrates in the cloud and delegates suitable subtasks to a model on your Mac." > "Local models run on your Mac's own memory and processor — the more capable your machine, the larger the models it can run." > "Privacy Gate is a small model that runs entirely on your Mac. It inspects anything headed to the cloud for personal or sensitive information — and if it finds any, you decide how to handle it before anything is sent." That would be huge 👀
0:21

PERPLEXITY 🔥: A new Hybrid mode is coming soon on Mac, letting local models handle some subtasks. > Gemma 4 (for 16 GB machines), Qwen3.6, and Perplexity's own model (For 32 GB machines) are currently supported. > "In Hybrid mode, Computer orchestrates in the cloud and delegates suitable subtasks to a model on your Mac." > "Local models run on your Mac's own memory and processor — the more capable your machine, the larger the models it can run." > "Privacy Gate is a small model that runs entirely on your Mac. It inspects anything headed to the cloud for personal or sensitive information — and if it finds any, you decide how to handle it before anything is sent." That would be huge 👀

🚨 AI News | TestingCatalog

41,281 Aufrufe • vor 21 Tagen

Today we're excited to announce Seezlo : A Meta-Gallery and Search Engine platform for Visual Art 🎨 ; powered by our very own brain-aligned machine vision model🧠 [ that was not trained on Art! 🤯]
0:59

Today we're excited to announce Seezlo : A Meta-Gallery and Search Engine platform for Visual Art 🎨 ; powered by our very own brain-aligned machine vision model🧠 [ that was not trained on Art! 🤯]

Artificio

176,374 Aufrufe • vor 3 Jahren

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.
0:54

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

NEXA AI

26,091 Aufrufe • vor 10 Monaten

Claude Code is now completely free forever 🤯 Just connect it to Ollama and run a local model like Google’s new Gemma 4. That means Claude Code agents can run directly on your computer with zero API bills and zero subscriptions. Google may have just ended AI subscription fees for good. 🚀
0:30

Claude Code is now completely free forever 🤯 Just connect it to Ollama and run a local model like Google’s new Gemma 4. That means Claude Code agents can run directly on your computer with zero API bills and zero subscriptions. Google may have just ended AI subscription fees for good. 🚀

Julian Goldie SEO

10,098 Aufrufe • vor 5 Monaten