Google, my favorite tech agency for causes precisely as this one, has executed it as soon as once more. It’s got the worldwide group of builders supercharged with one new product. This one is named Gemma 4.
What’s the hype? Nicely, a very open-source mannequin that competes with AI fashions 20 instances its measurement. And this one isn’t simply your common AI chatbot. It has been custom-built for superior reasoning and agentic workflows. That means, AI handles your total duties, in your system, even with out the necessity for the web.
Your private LLM, if you’ll.
After all, that was sufficient to get AI-savvy individuals internationally to strive their palms on it. And the outcomes are nothing in need of revolutionary. Right here, I share an inventory of a number of the high such tasks, that are easy but efficient use circumstances that individuals have managed to deliver to life, all because of Gemma 4.
However earlier than we dive in, here’s a little concerning the new AI mannequin by Google for these unaware.
Gemma 4: An Open-source AI Revolution
As I discussed, Gemma 4 is not only one other mannequin you open for chat and shut 5 minutes later. Google calls it its most clever open mannequin household but. And all this firepower is supposed to suppose via multi-step duties, work with instruments, generate code, and run by yourself {hardware}. That alone is sufficient to make the builders sit up.
After which comes the half that basically fuels the hype: Google says Gemma 4 delivers unusually excessive intelligence for its measurement. It is available in 4 sizes, with the bigger fashions rating among the many high open fashions on the earth whereas competing with methods far greater than them. Which means builders are out of the blue getting a mannequin that feels highly effective, versatile, and really usable for actual tasks. Open, multimodal, agent-ready, and lightweight sufficient to run in locations the place frontier AI often doesn’t. That’s precisely why Gemma 4 is beginning to really feel much less like a mannequin launch and extra like a shift.
You may study all concerning the new Gemma 4 right here.
For now, we will have a look at how builders around the globe are placing the succesful mannequin to make use of.
1. Run Claude Code with Gemma 4 for Free
This was a correct “wait, you are able to do that?” second for me.
A developer confirmed the best way to use Claude Code coding workflows with Gemma 4 operating domestically in your machine. Which mainly means you get Claude’s coding assistant by yourself laptop computer, with out paying per immediate and with out continually relying on the cloud. The setup makes use of Ollama to run Gemma 4 domestically, and the tweet frames it as a beginner-friendly course of that takes roughly quarter-hour on a laptop computer.
Why is that this cool? As a result of it turns Gemma 4 from “one other AI mannequin launch” into one thing immediately sensible. As a substitute of treating AI like a chatbot tab you open and shut, you may plug it right into a coding workflow and let it assist with writing, fixing, and understanding code proper in your system. And sure, the entire attraction right here is precisely what acquired individuals hyped about Gemma within the first place: no subscriptions, no API key drama, extra privateness, and far more management.
What is going on right here?
In quite simple phrases:
- Claude Code = the coding workflow/interface individuals like
- Gemma 4 = the mind offering the coding assist
- Ollama = the engine that runs the mannequin domestically in your laptop computer
The essential setup appears to be like like this
- set up Ollama
- obtain a Gemma 4 mannequin suited to your machine
- set up Claude Code in VS Code
- join Claude Code with Gemma 4 and begin coding domestically
2. Run Gemma 4 on an iPhone, Utterly Offline
After I mentioned ‘your private LLM’, this was the Gemma 4 mission I used to be referring to.
Think about an AI mannequin in your pocket. No web, no cloud connection, and no month-to-month price. Sharbel on X confirmed simply that – Gemma 4 operating instantly on an iPhone. Which means the AI mannequin shouldn’t be sitting on some distant server ready in your request. It’s proper there on the telephone, dealing with duties domestically like a pocket-sized mind.
The movement is easy and wild on the identical time:
- obtain Domestically AI
- discover Gemma 4 underneath the ‘Handle Fashions’ choice
- obtain it and use it for on-device reasoning and duties
That opens the door to every kind of non-public AI experiences. Assume non-public assistants, offline examine instruments, native notice evaluation, and even agentic workflows on the go. And that’s precisely why Gemma 4 has individuals so excited.
3. Run Gemma 4 on a Nintendo Change
In case your native LLM in your iPhone wasn’t sufficient, right here comes Gemma 4 operating on a Nintendo Change. Sure, an precise gaming console. maddiedreese shared Gemma 4 operating domestically on the machine at round 1.5 tokens per second. That velocity is clearly not constructed for high-pressure workplace work, however that’s not the purpose right here. The purpose is {that a} fashionable multimodal, agent-ready mannequin can now be squeezed into locations the place AI was by no means actually anticipated to dwell.
And that’s precisely why this use case hits so onerous. The workflow itself is easy in spirit:
- take a compact Gemma 4 mannequin
- optimise it sufficient to run on weaker {hardware}
- load it onto the Change domestically
- use the console as a tiny offline AI machine
Gemma 4 is making one factor very clear right here: highly effective AI is leaving the cloud and getting into private gadgets in every kind of weird, fantastic methods. At this fee, builders are mainly treating each display round them like a possible residence for an LLM.
4. Use Gemma 4 for Offline Audio Transcription on a Telephone
That is the place issues begin getting severely enjoyable. ai_for_success confirmed Gemma 4 E2B getting used for audio transcription on a Pixel 10 Professional. In plain English, meaning your telephone can take heed to a brief audio clip and switch it into textual content, domestically, while not having an enormous cloud setup that sends each request forwards and backwards. The submit notes that it helps as much as 30 seconds for now, which can sound small, however truthfully, even that is sufficient to present the place that is heading.
Why is that this thrilling? As a result of it takes AI out of the “chatbot field” and turns it into one thing your machine can do in the actual world. The movement is superbly easy:
- report or feed in a brief audio clip
- let Gemma 4 E2B course of it on-device
- get the spoken phrases again as textual content
- all with out relying absolutely on the web
Think about the chances it opens up: fast note-taking, voice memos, assembly snippets, lecture highlights, and even simply changing your random burst of genius into textual content earlier than it disappears. It’s not a full-blown studio transcription but. However as a glimpse of what small, native AI can already do on a telephone, that is completely wild.
5. Flip a Mac Studio into Your Personal Zero-Token AI Workhorse
This one is pure power-user power. jessegenet shared Gemma 4 31B operating on a Mac Studio, hooked as much as OpenClaw, and the road that basically jumps out is that this: “$0 in token bills now.” That’s the dream, isn’t it? A severe native AI setup that may chat, motive, and run workflows by yourself machine, feeling that fixed token-ticking at the back of your head.
What is going on right here is definitely quite simple:
- Mac Studio = the muscle
- Gemma 4 31B = the mind
- OpenClaw = the workflow/operator layer
- End result = an area AI assistant that feels far more like your individual system than a rented chatbot
Why that is such an enormous deal: most individuals expertise AI via an internet site or app. This setup flips that utterly. As a substitute of going to the AI, the AI lives with you, proper in your machine. Prepared for longer chats, {custom} workflows, non-public work, and repeated use with out per-prompt pricing stress from a hosted supplier. That’s when Gemma 4 begins wanting much less like “one other mannequin launch” and extra like the start of a correct private AI workstation.
6. Flip Gemma 4 right into a Actual-Time Imaginative and prescient Assistant in Your Browser
This one is very like a full-time AI assistant that’s approach smarter than the usual AI chatbots you utilize day-after-day. measure_plan constructed an app that mixes Gemma 4’s imaginative and prescient capabilities with Roboflow’s RF-DETR. The result’s a browser-based setup that may have a look at what your digicam sees and make sense of it in actual time. We are able to study from the submit that Gemma handles the precise understanding, whereas RF-DETR does the first-pass object detection. In different phrases, one mannequin spots what’s within the body, and the opposite explains what’s going on.
That combo opens up numerous enjoyable prospects actually quick:
- RF-DETR finds the objects within the scene
- Gemma 4 interprets these objects and provides context
- the entire thing runs dwell within the browser on an area machine
The super-cool mission reveals Gemma 4 doing far more than chatting or coding. It’s beginning to act like a visible mind. Level your digicam someplace, and the system can start figuring out what’s there, following the scene, and describing it again within the language of your alternative. Now think about such a system as an assistive device or a sensible digicam app that helps information you thru a course of that’s utterly new to you. The chances are merely wild.
7. Make Gemma 4 Deal with Actual-world Duties to Begin Your Day
Think about an AI that checks your calendar in the beginning of the day, after which sends messages that have to be despatched to your contacts, with out you even typing a phrase. OsaurusAI created precisely this in a mission with Gemma 4 26B. Working domestically at round 50 tokens per second, the AI was in a position to learn a calendar and textual content contacts. That could be a large bounce from “AI can chat” to “AI can truly do issues for me.”
The thought is easy:
- Gemma 4 does the pondering
- your apps like Calendar and Messages present the information
- the AI acts like a correct assistant on high of them
Why this issues: as soon as a mannequin can transfer this quick domestically, it stops feeling like a demo and begins feeling like an actual private agent. The sort that may test your schedule, discover the fitting particular person, and enable you to take motion immediately. All of this, with out sending each little request to the cloud.
8. Make Gemma 4 Audit an Whole Code Repository on a Tiny Setup
That is the form of demo that makes builders grin. UnslothAI confirmed Gemma 4 E4B (4-bit) finishing a full repo audit by executing Bash instructions and power calls domestically. The wild half is that it reportedly runs on simply 6GB RAM. That’s not “AI writes one helper perform.” That’s AI stepping via an actual codebase, utilizing instruments, and serving to examine the entire thing, similar to a mini coding agent by yourself machine would.
The setup is superbly easy:
- run a compact Gemma 4 mannequin domestically
- give it entry to primary instruments like Bash
- let it examine recordsdata, transfer via the repo, and motive over the code
- get a code audit while not having an enormous cloud setup
This one is far more relatable because it reveals Gemma 4 doing precise developer work, not simply code autocomplete cosplay. And the truth that it will possibly occur on such modest {hardware} is precisely what makes Gemma 4 really feel so disruptive. Highly effective AI is one factor. Highly effective AI that matches into odd machines is a revolution in itself.
9. Flip Gemma 4 into an Precise On-Gadget Agent with Agent Expertise
This one is a helpful function that Google itself launched together with the Gemma 4. Omar Sanseviero, who’s the Developer Expertise Lead at Google DeepMind, introduced Agent Expertise for Gemma 4 on X just lately. A lot because the title suggests, Agent Expertise work precisely like the abilities we’ve seen with Claude or different AI fashions. It’s an Android app expertise launched with Gemma 4, the place you may import completely different expertise and let Gemma 4 E2B motive via and use them instantly on-device. Which means your telephone is not only chatting again. It’s beginning to behave extra like an actual native agent.
What makes this thrilling is how easy the thought is:
- load expertise into the app
- let Gemma 4 perceive the duty
- have it use these expertise step-by-step
- all domestically on the machine
Agent Expertise takes Gemma 4 past chatbot territory and into one thing far more helpful: AI that may truly do issues in your telephone, not simply speak about them. And since it runs on-device, it additionally pushes the entire “private AI” thought a lot nearer to actuality.
10. Make Gemma 4 Flip Pictures into Songs
I’ve stored essentially the most enjoyable for the final. As soon as you might be executed utilizing the brand new Gemma mannequin for all of your work, it’s time to have some enjoyable with it. ai_for_success, in his X submit, shares the best way to just do that. He constructed an agent ability that lets Gemma 4 E2B name Lyria 3 and generate songs. Sure, precise songs. The submit says it really works for image-to-song, which suggests you may present the system a visible, let Gemma perceive it, after which have it set off music technology round that vibe.
The movement is tremendous easy:
- give it a picture
- let Gemma 4 perceive what’s in it
- use the agent ability to name Lyria 3
- get a music impressed by that visible enter
Why is that this such a cool remaining instance? As a result of it reveals Gemma 4 doing what all nice agentic fashions ought to do: not simply reply prompts, however assist create one thing new. One minute, it’s studying photos. The following minute, it’s making music out of them. That could be a artistic that reveals numerous human contact to it.
Additionally Learn:
Conclusion
These tasks present precisely why Gemma 4 feels greater than a traditional mannequin launch.
From coding assistants and offline iPhone LLMs to video understanding, repo audits, agent expertise, and even image-to-song technology, builders are already stretching it in all instructions. Sensible, or for pure enjoyable, Google’s new launch has change into the go-to AI mannequin inside days of its launch. And all of this, for one very potent motive – it runs domestically, all at no cost.
Such widespread traction early on is often the clearest signal {that a} product has landed effectively. Folks don’t simply check it, they begin constructing with it. Extra importantly, Gemma 4 is exhibiting what the subsequent part of AI might appear to be: extra private, extra native, extra controllable, and much much less depending on large cloud setups for any of your tasks.
After all, these are the early experiments. The true wave of Gemma 4 tasks could solely simply be getting began. So be sure to keep tuned to this area for extra such updates on the brand new Gemma mannequin.
Login to proceed studying and luxuriate in expert-curated content material.
