# fullmoon: local intelligence — user reviews

> 81 indexed App Store user reviews of fullmoon by Mainframe Computer, Inc., rated 4.40/5 from 100 ratings.

- Source: https://appshunter.io/ios/app/fullmoon-local-intelligence/id6727014156/reviews
- App overview in markdown: https://appshunter.io/ios/app/fullmoon-local-intelligence/id6727014156.md
- Rating breakdown: 5★ 75 · 4★ 11 · 3★ 3 · 2★ 4 · 1★ 7

## What do users think of fullmoon?

Overall sentiment: positive

**Pros**

- 🚀 Fast and efficient
- 🔒 Offline usage
- 👍 Clean and polished interface
- 👍 Works on older devices
- 👍 Friendly for less tech-savvy users

**Cons**

- 🐛 Compatibility issues
- 🐛 Downloading/installing models can be slow
- 🐛 Responses can be inaccurate or incomplete
- 🐛 App crashes when using certain features

**Commonly reported bugs**

- Incompatibility with iPhone SE2 and iPad Pro Gen3 despite supporting Metal 3
- Deepseek models not working on some devices

**Most requested features**

- Add support for saving/copying full chat conversations
- Expand functionality through Shortcuts integration
- Provide more advanced language models
- Allow users to remove/delete downloaded models
- Add support for attaching files and images
- Implement voice mode and customizable AI models

## Newest reviews (13 of 81)

### 4/5 — Great way to start, but feels unfinished.

*2026-07-16, version 1.2.0*

This is a great, free starting point for someone who wants to play with AI chat, but doesn’t want every query being sent and stored in the cloud. The models offered have apparently been optimized for Apple silicon, and they do feel more responsive compared to other apps. The suggested Llama 3.2 works well, as does its bigger brother (if your phone has RAM for it).

My single biggest gripe is the apparent lack of ability to give the models standard instructions, like a “system prompt.” That omission is enough to knock this to four stars for me. It’s not a major issue for the default Llama model, or the bigger Llama model. But the Qwen models can be VERY verbose. I don’t want to have to keep telling the model “be brief.”

There’s also some fit-and-finish issues that aren’t show stoppers, but could use attention.

First, the initial model download stalled around 60% of the way in. There’s no obvious way to abort and retry. I killed the app and tried again. Fortunately that had no ill side effects.

Second, once a model is installed, I didn’t find a good way to delete it. I wound up deleting the app (purging my chat history) and reinstalling to remove the extra model.

Lastly, the number of models are limited. I realize that’s probably because of the Apple silicon optimizations. In the fullness of time, it would be nice to have some more options, even if they were paid upgrades.

Thanks to the developer for the effort. Again, it’s a great start; I’m picky. They clearly know what they’re doing, and I’m sure they’ll get there eventually.

### 4/5 — This is the best idea ever but…

*2025-12-13, version 1.2.0*

It just needs new/more open source models as they get released! Please add more!

### 4/5 — Is what it is.

*2025-11-13, version 1.2.0*

This will do what you need it to do, no flashy stuff.

Don’t expect a genius, but it ain’t dumb either.

Thanks folks!

### 4/5 — It is almost perfect, great optimisation and UI

*2025-08-27, version 1.2.0*

The app works and looks great. Only if it would be possible to upload custom AI models, gguf support would be much appreciated

### 4/5 — New models and delete downloaded models

*2025-08-15, version 1.2.0*

The app has been great but could you add gemma3:270m and the possibility to delete downloaded models?

### 3/5 — Love the concept

*2025-05-15, version 1.2.0*

3 stars minimum. Love the concept, but unable to install on the Mac. Upon selecting a LLM package, there’s no ability to continue and install.

### 3/5 — Can't uninstall models

*2025-05-14, version 1.2.0*

If you install a model you can't uninstall it... App is now like 4 gb bruh

### 2/5 — Doesn't work offline

*2025-05-11*

To reproduce: 1. Download a model and let complete.
2. Exit app.
3. Turn on airplane mode, or turn off cell data and WiFi.
4. Open app and type to chat.
5. No response, long after the time interval it would have taken to start a response had the app been connected.

If a bug, please fix

### 4/5 — Really great but limited models

*2025-04-08, version 1.2.0*

I really like the app and it runs very well and fast on all my devices. I just wish there were options for larger models that might provide more accurate results

### 4/5 — Great to use in the bush with no internet

*2025-04-06, version 1.2.0*

Love what it offers.  Only request: allow me to delete downloaded models I don’t need.  Thanks.

### 4/5 — Local Models

*2025-04-04, version 1.2.0*

Hope can ad support for local modals

### 3/5 — Voice conversations

*2025-03-15, version 1.2.0*

It is recommended to add real-time voice functionality, allowing conversations in different languages.

### 5/5 — Perfect for offline activity

*2025-03-09, version 1.2.0*

I travel very often and having access to LLM locally it’s a blast. The app is very good. I could ask for integrating with online LLM thru my API keys but I really like that app is focused on having LLM local and not trying to do all and nothing. It’s fast, simple and reliable.

Pls also create a bsky profile so we can have a fullmoon community there !

## Most critical reviews (10 lowest-rated)

### 1/5 — 🚨 False advertising: does not work offline

*2026-04-19, version 1.2.0*

This app does not work offline. I have switched to Apollo for running offline LLMs. That one actually does work.
To reproduce: 1. Download a model and let complete.
2. Exit app.
3. Turn on airplane mode, turn off cell data and WiFi.
4. Open app and type to chat.
5. Chat returns a timeout error, long after the time interval it would have taken to start a response had the app been connected.

### 1/5 — Check your app, jerks

*2025-10-05, version 1.2.0*

Does not work on iPad Air 4th Gen, even though this listing says it does. That pisses me off.

### 1/5 — Likes to have Internet

*2025-09-22, version 1.2.0*

It kind of insists on being connected to the internet. Makes me wonder what it’s communicating too. 
If I turn wifi and data off completely then it works much better. But if I’m connected to slow internet then this app will hardly output any prints.

### 1/5 — Extremely basic AI, pretty much useless

*2025-04-02, version 1.2.0*

Not even the simplest task as summarising a paragraph or translating a small portion of a text from English to Spanish could be done properly by this app. The idea behind the project is the future - AI LLM running in our local computer without sharing our data with big corps. However, it is still far from being usable. I tried two different LLM (Llama 3.2-1b-instruct-4bit and DeepSeek-R1-distill-qwen-1.5b-4bit) and the results were simply wrong. The language models, although limited, are competent in small tasks.. when you tried it somewhere else. Here, they act like dumb, uneducated zombies. I was sorry that for some reason it didn’t work me. However, I’ll be around waiting for the next model.

### 1/5 — compatibility

*2025-02-09, version 1.2.0*

The app claims metal 3 is needed to run, however, iPhone 11 with iOS 18 installed is not supported, although A13 supports metal 3

### 1/5 — App is crashing

*2025-01-21, version 1.1.4*

Once I write a prompt the whole application crashes.

### 1/5 — Will not run

*2025-01-18, version 1.1.4*

iOS 18.2.1 on iPad Pro Gen3 and it will not run.
Message says it can only run on devices that support Metal 3.

### 2/5 — For less powerful phones

*2025-12-20, version 1.2.0*

My M2 iPad can handle bigger models, but Fullmoon’s in-app list is constrained to models they have packaged for mobile.

### 2/5 — Wird wohl nicht weiterentwickelt

*2025-10-10, version 1.2.0*

Nette Idee, wird aber wohl nicht weiterentwickelt

### 2/5 — Not actually local?

*2025-09-05*

To reproduce: 1. Download a model and let complete.
2. Exit app.
3. Turn on airplane mode, or turn off cell data and WiFi.
4. Open app and type to chat.
5. Chat returns a timeout error, long after the time interval it would have taken to start a response had the app been connected.

If a bug, please fix

## Most praised reviews (10 highest-rated)

### 5/5 — Can you update

*2026-07-26, version 1.2.0*

The app is great! Please update with the newest model. Thank you very much!

### 5/5 — Works well, but not on flights.

*2025-12-29, version 1.2.0*

This app is great. While it’s does work offline, the app requires a connection to hugging face, so it’s not always possible to use it during a flight.

### 5/5 — Great it can use offline

*2025-11-18, version 1.2.0*

Old but gold

### 5/5 — Great app

*2025-08-07, version 1.2.0*

It is very convenient to use, and the installation is quite simple. It would be even better if it supported the recently released GPT OSS 20B.

### 5/5 — Lack of newer models

*2025-06-15, version 1.2.0*

Using the app was elementary. It was super consistent, modern, and minimalist. Everything worked flawlessly. The models they have now are great for most people as whoever is going out of their way to download this app isn’t most people. But I think the app could really take it to the next level by adding more models. For example, DeepSeek’s 0528 would be an absolute game-changer!

### 5/5 — 😭

*2025-06-13, version 1.2.0*

Crazy ngl

### 5/5 — Great but …

*2025-05-27, version 1.2.0*

It is excellent for local usage of LLM models; however, adding more models, especially the new ones, would make it perfect. Thanks to the developers; your efforts are truly appreciated.

### 5/5 — ローカルで動くAIを見てみたいなら

*2025-05-27, version 1.2.0*

アプリケーションのUIは洗練されており、こういうものが初めてのユーザーでもローカル環境(それもiPadオンリーなど)でLLMを動かす体験を得るのにはとてもよいと思う。
その一方で、自分でモデルを自由に登録できないという制約もあり、枠の外に飛び出してみるということは難しい。そして使えるモデルの更新も止まっているようで、日本語に関していえばあまり賢くない子が並んでいるという悩みがある。
とりあえずニューラルチップをのせた端末でどんなことができるのかを試してみるのにはいいのではないだろうか

### 5/5 — awsome,but

*2025-05-14, version 1.2.0*

good, but i think you forgot button for uninstalling model.

### 5/5 — Muito bom

*2025-03-16, version 1.2.0*

Excelente, estava faltando uma opção assim na AppStore. Espero que ganhe melhorias no futuro, como opção de voz, ouvir o texto recebido, etc.

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-11.*
