Google AI Edge Gallery
Private, Fast, Offline AI







How much does Google AI Edge Gallery cost?
Prices are current as of 12 Sept 2026.
Google AI Edge Gallery has no in-app products on record in the United States.
10+ alternatives to Google AI Edge Gallery
![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Rating / 5 | 4.0 | 4.8 | 4.9 | 4.7 | 4.8 | 4.5 | 4.7 | 4.5 | 4.4 | 4.1 | 3.6 |
| Reviews | 706 | 241K | 213K | 48K | 40K | 9.5K | 4.3K | 3.4K | 2.2K | 624 | 133 |
| Released | 2026 | 2025 | 2024 | 2025 | 2025 | 2021 | 2025 | 2025 | 2024 | 2024 | 2026 |
| Monthly price | — | $39.00 | $39.00 | $49.99 | $7.49 | — | — | $30.00 | $8.49 | — | — |
| Annual price | — | — | $180.99 | $239.99 | $72.00 | — | — | $143.99 | $84.99 | — | — |
| One-time price | — | $20.00 | — | $19.99 | — | — | — | — | $249.99 | — | — |
The going rate for each plan in United States, in its own currency, shaded from the cheapest price on the row to the dearest. Plans fewer than four in ten of the priced apps sell are left out.
Google AI Edge Gallery reviews
4.0 out of 5, based on 706 reviews.
What people like
- Runs AI models directly on your phone
- Works completely offline without internet
- Very fast response times on new devices
What they complain about
- App freezes and crashes constantly
- Text is not selectable or copyable
- No native iPad app support yet
Eleventh of July
Google Gallery on iPhone 17 pro. With the new Gemma 4E4b with default settings except for switching halfway through to speculatively decoding and think it made it through an 18 question Q&A
Impression
💜
Nice app, but privacy concerns
It works pretty well, and lower memory requirements, depending on the task, than loading the full model in other frameworks But: Why does a local AI app which runs on device (purportedly) give me the functionality to thumbs up or thumbs down the response??! personally, if I’m running it on device and powering the matmuls by draining my battery I want the model running in a Faraday cage
Zero config sovereignty
The configs return to default every time you close the app. Why? Also the lack of gestures is baffling
限制太多。
沒有 iPad OS 模式,又只有小模型能裝,好可惜。
Works great for local LLM usage
This is a great app if you want to be able to run Gemma models locally. I’m really surprised at how fast it runs—it made a recipe for black bean enchiladas in just 22 seconds on my iPhone 17 pro. It’s not the most user friendly and is oriented towards people testing stuff out but is great for what it is
iPadOS
native iPadOS application please.
Honestly a good idea from Google: Local AI
[TL;DR] Great app, but some bugs need to be addressed. Could use .safetensors model support as well. I honestly think this app is genius. Let’s say that you’re out in the middle of nowhere and you need to see what type of food is safe to eat. You upload an image, and let the Gemma model do its thing. Or, when you’re back online, you can use the Agentic mode where it can access the internet (with custom plugins). You might be wondering why this review it only 4 stars. The bad part: the app is super buggy on an iPhone 15. After a second prompt, the app freezes. Want to change the model’s settings? Nope; another crash. And the problem with this app is that you can only use their special litertlm format for the models (the reason why is that it manages the orchestration, kv cache, and memory mapping all in one). It would be great to see safetensors support. Also the desktop app is bugged as well. It’s just the iPhone app but ported to Mac. So it’s just an iPhone simulator (basically). Just don’t use this on desktop; use ollama, lm studio, or vllm instead. In conclusion, this app has great potential, but would need some improvements.
Does not work in iPad
I loved it in my iPhone but the app is ugly in Mac M-3 iPad. Fix it please
Support for low RAM Iphones
If Low RAM optimised models are made for Iphones with 4 and 6gb RAM it will be awesome
We need an iPad app!
C’mon guys.
Ipad version
Please add ipad version
App Freezing
I’m enjoying testing out all the open weight models, but I’m only able to keep the app from freezing solid for a couple of minutes. Doesn’t seem to be related to a specific model.
Needs Improvement
One of the glaring issues, and the most important one I’ve encountered, is for the skills. For example, opening up the reminder skill will automatically prompt the AI to create a reminder at 9am tomorrow. A simple example sentence would suffice, rather than a performative prompt to show users what it does if the skill wasn’t direct enough. This goes for the other skills as well.
Add text-only mode (download without mmproj)
Please add an option to download Gemma-4-E2B-it without mmproj (text-only mode, no multimodality). This would allow it to run on devices with 4 GB of RAM. Currently, the app blocks installation even though the model works fine in text-only mode — I've tested it in another app.
Why should I be complaining
I am using this app on an iPhone 14. I thought this was like Gemini and upon downloading and starting I was pretty disappointed. The AI didn’t seem that good and the app kept freezing after a couple prompts. When I looked into it, I realized this was actually Google‘s Gemma four model instead of running in a data center around on my device, which was mind blowing. Even with the freezing. I’m gonna take this experience like a plane. You can’t really complain when you’re flying 4000 feet in the air 12 times faster than anything on the ground. In AI model that runs on my device off-line is exactly like that. I’m excited to see where this type of projects by Google go!
Issues with screen reader accessibility for VoiceOver
This app needs significant improvements to accessibility regarding people who are blind and need screen readers, I tried this with VoiceOver and this is extremely hard to use. I struggled just to get the model to chat.
Dear Early Adopter,
Fast, private starting point with constraints in the nascent building stage. Thank you, Google!
同じ言葉を繰り返します
同じ言葉を繰り返してしまう症状があります
The text selection feature is broken in the iOS app. I cannot copy text directly, which is very frus
I am using the iOS app, and I am experiencing a major usability issue. When viewing responses, the text is not selectable. I have to take a screenshot and use Live Text to copy the information, which is a major annoyance. Please fix the text selection functionality
Very good
It would be even better if it supported multiple languages.
Missing browsing feature
1) Give it the ability to optionally browse/search the internet it’ll be epic. Without that, it’s useless. 2) UI and UX are ugly.
Resuelve pero…
Cuando le necesitas no abre, no carga o simplemente no levanta
Seems like it could be good after the issues are fixed
I am using this on a iPhone 16 pro and it freezes every time I try to use it, so for now it is not functional. It does seem like it could be great, if the bugs are worked out.
希望支持更多语言
软件很好用、就是界面还是英文一种语言、
Best Local Model app for Iphone right now
Can you please add more model from hugging face, It seems like that function is lack of the android version
FIX THE FREEZING
The App freezes as soon as I try to do anything! I paid for my iPhone 17 pro max & the app doesn’t even work properly on it
Issue with downloading models
When trying to download models, the download completes immediately, and when i try to use it crashes the app
有待完善
目前体验一般,多问几个问题就卡死了
Good but:
Keeps freezing up on my phone, using Gemma-4-E2B-it on IPhone 16 pro max (26.4.1)
Exciting
We fo sho test bunnies im enjoying it tho excited to see what they can bring
Crashes
Crashes on Gemma 4 using any use case
freezes
I am using an iPhone 16 Pro Max. It is functional, but it occasionally crashes/freezes, requiring me to exit and restart the application to continue using it.
Buggy
Please fix make implement to many freezing issues on iPhone 15 pro
Freezes up
That app works but on occasions when trying to do a chat the interface simply freezes up requiring the app to be closed and reopen…
Works well with 1 missing feature
I love this app for testing and running local ai models. But the lack of a chat history really sucks. Good interface. This app is meant for testing models though not for persistent chats. But I would use it often if it was persistent.
Needs more optimization
I really wanted to love this app on my M3 iPad Air. I even downloaded all the large models (2.5GB to 4GB), but unfortunately, the speech-to-text and grammar accuracy for Persian isn't quite there yet. The M3 chip is powerful, so I hope the developers can improve the Farsi language models in future updates. Deleted for now, but I'll keep an eye on it!
Issue with 'Ask Image' prompts: Unable to select and copy partial text
I can't select and copy a specific part of the 'Ask Image' prompt. It forces me to copy the entire text, including the rest of the conversation. This needs to be fixed.
It’s great but one problem is wrecking it
So i LOVE the app but every time i chat with it it freezes so yeahhh…
It’s local, and that’s the best part
Yes, it is smart. If you’re on a smaller iPhone with less RAM, it knows which models are available, and the models do have a lot of baked intelligence. I tried to use the one for iOS specific actions, there’s still barely any functionality. The pre-created prompts that are listed are almost all that it can do. I tried opening some apps, I tried creating an email. I tried changing any settings. It was basically utterly useless. Small local prompts that don’t memory are basically the best they can do at this point. And the worst part is there is no widget available to quickly call while still on the home screen. You actually have to go into the app in order to do a basic function that is faster to do with the widgets. It’s still a solution looking for a problem.
Very good
Very good
Not truly “offline”
If you need an internet connection to “initialize” the model every time you use it, then it’s not truly offline. Not useful at all if you actually don’t have a connection. Fix your marketing language or the bug.
Optimise the app display for iPad desktop view
I am getting a mobile display on my iPad. M1 iOS 26.4 can you please optimise it for iPad? Desktop s
La app se bloquea y el móvil se calienta
Esta app está muy bien, pero tiene algún problema: se bloquea un poco cuando escribo en el chat mientras estoy parado, y mi móvil se calienta un poco.
Interesting
Give us web search and/or the ability to make our own skills.
Tiny garden didn't work
Can't open it after download
Model download is throttled
I have a high speed Internet, but looks like the download is throttled at the source and it’s pathetically slow
I hope to see the Chinese-language UI interface implemented soon.
language chinise zh 我们需要中文UI界面😊
Gemma 4
Gallery locks up and crashes on iPhone after 2 or 3 sole questions currently. I'm sure will be fixed in no time.
Improve your frontend
The chatbot interface failed to render markdown, latex, code block, etc. It’s kinda disturbing. Please fix it
Google AI Edge Gallery FAQ
- Is Google AI Edge Gallery free?
- Yes. The app is free, in all 172 countries it sells in, and it sells nothing inside it.
- Does Google AI Edge Gallery have a free trial?
- No. None of its offers (US) come with a free trial.
- What are the best alternatives to Google AI Edge Gallery?
- Manus - AI Agent & Automation (4.8 from 240,518 reviews, premium from $9.99), Kimi - Kimi K3 is Live (4.9 from 213,054 reviews, premium from $19.00) and Genspark AI Workspace (4.7 from 48,040 reviews, premium from $19.99).
Google AI Edge Gallery download
Last updated 1 month ago.
Google AI Edge Gallery sells in 172 countries. It was released 7 months ago, on 25 Feb 2026. It holds a 4.0 rating from 706 reviews.
Supports 94 languages: English, Afrikaans, Akan, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Basque, Belarusian, Bangla, Bosnian, Bulgarian, Burmese, Khmer, Catalan, Croatian, Czech, Danish, Dutch, Estonian, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Kannada, Kazakh, Kinyarwanda, rn, Korean, Kyrgyz, Lao, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malay, Malayalam, Maltese, Marathi, Mongolian, Nepali, Norwegian Bokmål, Odia, Oromo, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Samoan, Serbian, Chinese, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Filipino, Tamil, Telugu, Thai, Tigrinya, Turkish, Turkmen, Akan, Uyghur, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Xhosa, Yoruba, Zulu.
How much does Google AI Edge Gallery make?
Third-party estimates for the last 30 days, worldwide — not the store's own figures, which Apple publishes for nobody.







