# LatentChat - Assistant LLM — user reviews > 27 indexed App Store user reviews of LatentChat by Emanuele Delirio, rated 3.80/5 from 28 ratings. - Source: https://appshunter.io/ios/app/latentchat-assistant-llm/id6733216453/reviews - App overview in markdown: https://appshunter.io/ios/app/latentchat-assistant-llm/id6733216453.md - Rating breakdown: 5★ 16 · 4★ 3 · 3★ 3 · 2★ 0 · 1★ 6 ## Newest reviews (7 of 27) ### 4/5 — One of the best *2026-05-11* This is classed with Locally Ai and Pocket Pal and is packed with best on device LLM functionality plus you can import your own gguf models, use voice, use image and use docs. Shortcuts integration is buggy but the app is still 9/10 ### 4/5 — Pretty good. A few issues. *2026-01-05* It’s a good app that I’m using to connect to my LMStudio server at home. It connects well. It streams the response (rather than waiting for it to be finished before output) so that means you don’t get timeouts. It gives you some controls over server settings too, like temperature, etc. I don’t get caught with the whole SSL trap either, like many other apps. App specific issues are rare. It drops content out of chats if you leave the app and return. It has no user control over colours or appearance. Bottom line: it’s a good app that seems like the first version. With a few improvements, it could easily be the “go-to” app for this type of thing. I also tried loading an LLM onto the phone. It worked well enough but I didn’t really push it. I never did figure out how to load my own LLM onto the phone because I didn’t care enough to keep trying. I already have my LMStudio server. ### 4/5 — Best I’ve used *2025-04-19* This is an excellent app for on-device LLMs. It functions seamlessly, and its interface is straightforward, polished, and purposeful. The only feature I feel is missing is text-to-speech for the responses. ### 4/5 — Best I’ve used *2025-04-15* This is an excellent app for on-device LLMs. It functions seamlessly, and its interface is straightforward, polished, and purposeful. The only feature I feel is missing is text-to-speech for the responses. ### 5/5 — Basic but works consistently. *2024-12-17* Still pretty basic feature set but it’s works fluidly and having it perform as expected is worth the money over other alternatives that seem to still be working out the kinks. ### 5/5 — Just Scratching The Surface *2024-12-08* Pleasantly surprised. Lots of features implemented well that others are missing. RAG is great and perfect for shortcuts. Keep going! ### 5/5 — Helpful app smooth *2024-11-16* Great app many features, enjoy using own models, rag is implemented well, updates, nice ui, a+ ## Most critical reviews (10 lowest-rated) ### 1/5 — Horrible. Worthless. *2025-11-21* I just wasted 4.99 **Developer response:** Hello, if you want to share why you’re not happy with the app, feel free to contact me by email. ### 1/5 — Avoid this and look elsewhere. *2025-08-06* I regret spending a single dollar on Latent Chat. The platform constantly crashes, and none of the models work reliably. Most bots are broken or give errors, and you can’t upload or use your own models – which makes it super limited compared to other platforms. Even basic functionality like customization or smooth conversation often fails. It’s frustrating and not worth the time or money. **Developer response:** Hello, sad to hear these performance issues. Feel free to contact me to share the models that are not working for you, maybe your device is not capable enough for some of them. The models available in the app have all been tested on iPhone 16 Pro and the smaller ones on iPhone 11. One remark: the app does allow you to use your own models, you simply need to import them from the model manager! ### 1/5 — Very broken app *2025-06-11* Ya this app backgrounds lm studio streaming but as soon as you leave a chat no more consulting that chat. Start a new one. Oh you were invested in that? Too bad so sad. Did you want image and file input for your local lms? well it doesnt have that either, look somewhere else. **Developer response:** Hello, that’s good feedback. I implemented these features in the latest update: you can keep using the remote chat even if you close it, and you can also add an input file. Vision capabilities (input images) are still not supported but this might change in the future. Thank you! ### 1/5 — Doesn’t work *2025-05-12* The app fails to load. I’ve not been able to use it. **Developer response:** Hello, sorry for that. contact me at info@latentlake.com so we can solve your issue. Feel free to specify the device you are using and models you are try to load. There was a problem with a previous version of the app but it has been solved in the latest update ### 1/5 — One star *2025-04-23* Keeps crashing, causes phone to freeze on just even one question. **Developer response:** Hello, sorry to hear that. Try updating to the latest version, there was a problem loading some models! ### 1/5 — Imposible de iniciar. No funciona. *2025-02-23, version 1.3.8* Qué solución me dan. ### 2/5 — Need no port option+API key *2026-02-01* Please have an option for Ollama without a port or the ability to change the OpenAPI URL for my use case. **Developer response:** Hello, if you remove the port from the ollama connection, the url will be formed without a port; the field is not mandatory and can be set to empty. You can also create a new connection with a name that starts with “ollama” and it will make requests compatible with it, again leaving the port empty. I will add more configurations and settings to make this more clear. However if I misunderstood your use case, please let me know and I’ll be happy to help: info@latentlake.com ### 3/5 — Need hands free TTS and STT *2026-02-08* Voice quality is good but requires manual intervention to send and receive voice. Please add automatic voice TTS and STT response. **Developer response:** Hello, if you remove the port from the ollama connection, the url will be formed without a port; the field is not mandatory and can be set to empty. You can also create a new connection with a name that starts with “ollama” and it will make requests compatible with it, again leaving the port empty. I will add more configurations and settings to make this more clear. However if I misunderstood your use case, please let me know and I’ll be happy to help: info@latentlake.com ### 3/5 — Needs to be optimized *2025-03-29* Beautiful UI just Lacks adjustability should take notes from LLM Farm, but this is the winner once more adjustability is added and theming perhaps ai friends panel etc take it the next step dev!! ### 3/5 — cannot load other LLMs *2025-03-10* It is great but cannot load LLMs other than the default one! Please fix the bug! ## Most praised reviews (10 highest-rated) ### 5/5 — Überraschend leistungsstark und intuitiv *2026-07-28* LatentChat hat mich wirklich positiv überrascht. Die App ist übersichtlich aufgebaut, reagiert schnell und bietet eine sehr angenehme Nutzererfahrung. Besonders gefällt mir, wie flüssig die Interaktion funktioniert und wie gut die Antworten strukturiert sind. Auch technisch wirkt alles durchdacht – keine Abstürze, keine unnötigen Ladezeiten. Für den täglichen Einsatz, egal ob für schnelle Fragen oder komplexere Themen, ist die App absolut zuverlässig. Klare Empfehlung für alle, die eine moderne und leistungsfähige Chat-App suchen. ### 5/5 — Fixed *2026-06-02* Latest update fixed the menu dropdown issue. Much better **Developer response:** Hello, thanks for the feedback. I found the issue with the dropdown menus and I will fix it in the next update. I’m not able to replicate your second issue, I will investigate more but feel free to contact me to share more details at info@latentlake.com ### 5/5 — The Best *2026-02-08* I have tried all the local model apps. This is the only one with such fine control, plus importing custom models. The Siri shortcut functionality is the slam dunk. Most of the other competitors don’t even get updates anymore. Love to see this one is going strong. ### 5/5 — Works really well *2025-12-19* I am a full stack developer and recently started working with offline models using OLLAMA and open WebUI, I wanted similar functionality on an iOS device, I must say I am impressed with this gem of an app, you have to play around with it , but once you figure out the RAG part (most important), it ROCKSSS!!!, great app for offline work.. BUY IT 😂😂 ### 5/5 — Small LLM with RAG on you phone! *2025-11-02* Using RAG is simple and most models handle even huge book or many articles well. ### 5/5 — Great tool for creators *2025-10-26* After tinkering around I seem have got it 🤞🏽Turned out to be exactly what the devs said. I’m on an iPhone 12 Pro Max the app runs smoothly with default or recommended models. Need bigger models? Use remote server to offload your your Mac. I initially wanted a refund but I changed my mind. IF YOU KNOW HOW TO SET IT UP IT REALLY WORKS ### 5/5 — works well, good models range *2025-05-24, version 1.4.6* way better than other local LLM running apps, runs smoothly and has good features. just wish we could set up our own system message input format as eg. Mistral doesn't work with the default one. ### 5/5 — The power is in it's RAG *2025-02-19* Took me a bit to realize what the rag function was for, but I eventually understood that basically you can feed it your own knowledge it the llm. Great stuff. And you can load up your own.gguf files from huggingface or wherever else. Highly recommend this one. ### 5/5 — Love the look of this app *2025-01-11* This app is great! It runs so smoothly! It just feels natural to use! Also having a local assistant is super nice! ### 5/5 — Almost Perfect⭐️⭐️⭐️⭐️⭐️ *2024-12-25* This app loads faster and smoother than other local LLM’s. It does almost everything a cloud based AI can do and the developer is open to improvements. This is the only on device AI (at this time) that uses RAG with easy implementation and works 100%. Keep the updates coming and thank you for this local AI gem. --- *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 2026-08-27.*