# Liquid Apollo — user reviews > 146 indexed App Store user reviews of Liquid Apollo by Liquid AI, Inc., rated 4.50/5 from 599 ratings. - Source: https://appshunter.io/ios/app/liquid-apollo/id6448019325/reviews - App overview in markdown: https://appshunter.io/ios/app/liquid-apollo/id6448019325.md - Rating breakdown: 5★ 477 · 4★ 51 · 3★ 18 · 2★ 14 · 1★ 39 ## What do users think of Liquid Apollo? Overall sentiment: positive **Pros** - 🚀 Great app - 🚀 Works well with OpenRouter - 🚀 Excellent for running local models - 🚀 Convenient one-time purchase - 🚀 Clean and intuitive UI - 🚀 Supports voice chat and shortcuts **Cons** - 🐛 Crashes frequently - 🐛 Glitches when editing messages - 🐛 Inconsistent message formatting - 🐛 Slow performance with larger conversations - 🔒 Unable to disable app transport security - 🔋 High battery consumption with some models **Commonly reported bugs** - Unable to download Liquid Models - Deleted locally installed models - OpenRouter support crashes the app - Voice list doesn't load all available voices - Backspace lag leading to unintended text deletion - Inconsistent behavior when using code blocks **Most requested features** - Add support for more open-source models (e.g. Gemma 3) - Implement image generation and upload functionality - Allow scheduling of asynchronous tasks - Integrate with Hugging Face model repository - Provide built-in prompt library - Add MCP (Multimodal Conversation Protocol) support - Enable direct OpenAI API integration - Improve voice chat functionality - Add option to delete all chat history - Implement search and filtering for chat history ## Newest reviews (14 of 146) ### 3/5 — Solid *2026-09-06, version 2.2.4* I really like it. But I really need a "thinking effort" option and custom API image attachment support. Would also like to use the better Siri voices to TTS. ### 3/5 — Barebones for connecting to self-hosted AI *2026-08-28, version 2.2.4* There's no option for tool use ### 3/5 — Parameters and stop tokens *2026-08-22, version 2.2.4* Parameters and stop tokens do not work when using a custom backend (llama.cpp on my home computer). I could not find the option to add either of the aforesaid at all when running a local model. Please fix. ### 3/5 — Could have more *2026-05-25, version 2.2.3* Could have a lot more features, like being able to download your own custom model or import your own gguf or safetensors file. It’s a good nice designed app though i would like more customization options for it ### 4/5 — Does not work *2026-05-21, version 2.2.2* I paste my OpenRouter API key and select a model. Any model. The result is always the same, a vague error that there is a provider error and no clue what that error is. No help, and contact is only through a small form. Some help would be nice, or at least a clue on what the error is. ### 3/5 — Janky *2026-05-16, version 2.2.2* Web search doesn’t work most of the time and image generation doesn’t work at all. ### 4/5 — Solid *2026-05-13, version 2.2.2* I really like it. But I really need a "thinking effort" setting. ### 4/5 — Great idea, needs to mature a bit *2026-05-03, version 2.2.2* Still some quirks to work out in the UI, inconsistencies, weird UX flows, etc. overall, love that you can download models to run locally (even though it's only LFM and Qwen 3 models), and can connect to an openai compatible custom endpoint. Even comes with web search built in. 5 stars if the custom endpoints also accept images as input. ### 2/5 — crashes *2026-04-27, version 2.2.2* The app crashes on my iPhone 16 Pro Max when I use a custom backend the answer comes back but immediately after that crashes, it seems to work fine on my iPad Pro M2 ### 4/5 — More models *2026-04-09, version 2.2.1* I know this is made by Liquid AI and they want to promote their model, but this is the best mobile UI for local AI. Since you already have qwen, please also add gemma 4 if possible. ### 5/5 — Great work ! *2026-03-27, version 2.1.9* Wow ! Love it. Nice font and ui/ux give a really nice alternative too other generic chat. I would love to see sync from phone to on prem Apollo web browser. So I can switch from phone to desktop and keep convo. ### 3/5 — Stop Backing Up Models to iCloud *2026-03-24, version 2.1.9* Hey guys, you’re backing up the models to iCloud, taking up huge amounts of storage. Might want to turn that off. ### 5/5 — This should be way more popular *2026-03-24, version 2.1.9* Not gonna lie been on the app for about 35 seconds already downloaded 2 model they both work pretty fast. This is the first mobile app I’ve used to try local ai and I was psyched to see the LMF two family on there and it’s just like wow good job. ### 4/5 — Very strong contender for best app on my phone *2026-03-13, version 2.1.8* Once the rough edges of this app are ironed out and the feature updates come in this is gonna be an essential part of AI power users lives ## Most critical reviews (10 lowest-rated) ### 1/5 — Background Phoning Home *2026-08-23, version 2.2.4* Apollo restarts itself in the background (even when exiting the app) and proceeds to phone home all by itself: leap.liquid.ai (also sentry.io). There is absolutely no reason for this app to be phoning home. And even more so when it is running in the background inadvertently. And it’s impossible to kill in Activity Monitor. Users Beware. ### 1/5 — Either adopt AI or don’t; this is not a viable alternative *2026-06-01, version 2.2.3* I’ve tried about every AI tool imaginable over the past 2 years and based on my experience, I am dumbfounded as to why this is so highly rated and now with Apple Intelligence becoming at least functional over the past few weeks, why this will remain an option in the iOS store. There’s legitimately not one use case for it since it botches everything you ask it to do. That said, I also understand the intention behind the app and applaud that but by AI’s very nature, it’s efficacy is inversely correlated to privacy —the more privacy protections you’re willing to waive, the better the underlying AI will perform; nothing will change that as Edge AI is largely a farce @Apple - stop censoring my reviews. The next time you do I’m reporting your conduct to the AG’s and FTC’s offices ### 1/5 — Good, but… *2026-05-26, version 2.2.3* It’s a good app, but what is going on with the text. It’s so small and just overall hard to read chat interface. If they can fix that it’s 5 star. Even if you adjust the size it gets all out of place when you try and select text. No idea what is going on, does nobody test it haha ### 1/5 — Bad Context size *2026-05-03, version 2.2.2* I have tried to add some promts for better conversation, but any bot starts to not see my messages, he can only see promt. The context size is very small, and also I think that instructions are sending to chat every time I try to message my questions, not only 1 time at the start of conversation. Better use ChatBox ### 1/5 — Can’t retain temp settings *2026-04-09, version 2.2.1* As title says ### 1/5 — This is great but please FIX the WEB SEARCH asap. *2026-04-01, version 2.2.0* I love it . I do. But please fix the web search. Use the phone browser as connect if need be or implement web fetch. PLEASE PLEASE PLEASE ### 1/5 — Glitchy *2026-03-13, version 2.1.8* When you’re going back to scroll through the chat to review what was said, it will jump to the bottom or to the top abruptly without warning. It won’t stay where you want it. Completely unusable. ### 1/5 — Still censors normal basic stuff *2025-12-25, version 2.0.0* So stupid ### 1/5 — How to remove your stupid system prompt? *2025-10-09, version 1.1.8* How to remove your stupid system prompt? ### 1/5 — OpenRouter support does not work *2025-09-08, version 1.1.5* Attempting to use cloud based models via OpenRouter instantly crashes the iOS app, and in MacOS the send button is unresponsive. Doesn’t appear that OpenRouter is usable. ## Most praised reviews (10 highest-rated) ### 5/5 — Ai *2026-08-07, version 2.2.4* Liquid Apollo offers local ai models for iPhones. I tried 1.5b parameters models and they worked well, but I don’t recommend for code because of hallucinations. ### 5/5 — Great *2026-07-20, version 2.2.3* Amazing ### 5/5 — Amazing *2026-07-15, version 2.2.3* Incredibly powerful app. It truly hits different to talk to an AI running on your smartphone when you’re out in the middle of nowhere with no internet connection whatsoever. The models are very impressive with their capabilities for the small parameter count. REQUEST: please allow us to switch the default model. It resets after every new chat! When using this with a custom backend it takes like 4 clicks each chat just to switch it, which makes an otherwise great feature more annoying to use. ### 5/5 — Brilliant Concept (I have some suggestions) *2026-06-29, version 2.2.3* Honestly, this app utilizes “Apple Intelligence” (or, Apple’s integrated support for local AI via certain hardware and software additions and changes) far better than any other application. It literally allows you to use supported models locally, on device, free of charge. Apple themselves is yet to even improve Siri and allow their own very flawed voice assistant to make use of this. I paid for the new iPhone assuming this would be utilized, and so far, this app is probably the only application which makes ample use of that. Suggestions: - Enable sideloading of supported models by means of HuggingFace access (gguf, safetensor, etc… whatever is supported) - Addition of more support for inference or API based model providers (aside from OpenRouter, perhaps Kimi/Z.AI/OpenCode’s plans which offer more reasonably priced access, Venice AI, etc) - Addition of more tools (such as how the web search tool works; adding more would be nice) - Enable MCP support (the search tool is cool, but not good enough — enabling the use of MCPs could help; perhaps add an addon store) - Enable scripting for custom agents, tooling, etc (I’d prefer an “OpenCode”-esq agentic experience over the current agent, so customization of behavior, guiding reasoning, allowing custom tooling using premade SDK and otherwise, etc would be very cool) I was thinking about making an open source version of this app and integrating such features, but clearly the developers of this application are competent and can do it themselves as they wish. ### 5/5 — Bonsai teraney 8B *2026-06-21, version 2.2.3* Please add bonsai teraney llm 8B as the only app that has it is local ai by lm studio which its system prompt only allows 1000 tokens I use very advanced system prompts and need infinite system prompt token limit. Please add this model as its fast and works well on my iPhone 13 Pro ### 5/5 — World Changing *2026-05-26, version 2.2.3* Liquid’s models are going to change the world. Imagine the entire power of Anthropic plus Open AI in the palm of your hand powered only by your phone. ### 5/5 — Minimalistic and powerful *2026-05-08, version 2.2.2* Everything perfect. The only thing i miss is the setting to hide reasoning process. ### 5/5 — Works very well, much better than other similar apps such as LocallyAI *2026-04-25, version 2.2.2* Title says it all. ### 5/5 — My new Goto *2026-04-24, version 2.2.2* I feel like i have tried every local AI app in the app store and this one punches beyond anything i have tried. On iPhone 14 pro, so outdated and yet the experience is flawless. Web search works better than most I’ve used. All the models are quick and optimized. I am looking forward to the addition of search for vision capabilities. Once that is implemented in both vision and voice chat, we have a winner. ### 5/5 — good job. need a terminal plugin *2026-04-08, version 2.2.1* 這正是所需的：能夠同時運行雲端和本地大模型。如果能有直接運行大模型的終端插件或腳本，那就更好了。 This is exactly what is needed: the ability to run both cloud and local LLMs simultaneously. It would be even better if there were a terminal plugin to run the models script directly. --- *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 2026-09-11.*