3sparks Chat User Reviews

Name: 3sparks Chat
Rating: 4.25926 (27 reviews)

3sparks Chat

3sparks labs llc

🔧 Utilities

📊 Productivity

Top reviews

Most Recent Highest Rated Lowest Rated

Updates = Broken

Every time we get an update, more things get broken. Now the app freezes and locks up during chats… you have to close the app and restart it, and your last prompt is gone and you have to redo everything. Can’t use it like this.

LateToThePartyDave

16 days ago

Intuitive and great support

Secure, easy to use with great features. Very good value for money.

yis90

a month ago

Works great with local LM Studio

The developer seems to be constantly improving the app and for me it meets many of my used case needs with a back in connection to LM studio.

I very much appreciate the image enablement.

IT Manager

3 months ago

Only Englisch keyboard layout

The language and layout could be also in German for exampel.

Markissen

3 months ago

Useful remote chat

Easy-to-use app to connect your iPhone to the local LM Studio server. Especially nice is its ability to save and use different system prompts from within the app.

Auf_dem_Mond_ein_Feuer

6 months ago

Save your money!

After a week still can’t get it to work, while others chat apps have no problem with my server, waste of time and money.

bcriss50

7 months ago

Response from developer

Hi there, please reach out from the help menu in app and I can help you figure out what’s wrong.

Works

Connection was a breeze with LM Studio and Tailscale. Please consder incorporating audio input for prompting.

rhabarbermarmelader

10 months ago

Stay away from this app

I just got charged by this. I cannot cancel a subscription and there is no way to do this in the app either.

goofymonkfish

a year ago

Response from developer

Hi there, our app doesn’t offer any subscriptions. If you’d like a refund, you can contact Apple, and they’ll be happy to process it for your purchase.

Not worth the money

Does not work in prohibited countries without VPN. Anthropic does not support the latest models, although there is a «Fetch models» button. After a couple of messages, LLM stopped responding and then the chat history stopped loading at all.

Aleksey Shelementev

a year ago

Great start, but needs more features.

Great job overall. However, a few things are really annoying. The default token limit is too small. I’d like to set the default per connection. Another annoying one is that Gemini doesn’t use grounding. Please enable Search grounding for Gemini models. The last annoying thing is that there’s no iOS Live Activity corresponding to running queries. It’s really annoying to have to keep the app open for the query to not be interrupted.

Dùn Èideann

a year ago

Local PDF access

So far works very well and was able to provide a picture to a local model that understands pictures. Also was able to provide a PDF via web URL link. But choosing Text file cannot provide local PDFs. Adding an option to provide local PDF files and drag and drop of files into the chat would be a great option!

VicenteSilvestre

a year ago

Response from developer

Thank you! I’ll see how I can add support for more file types.

Still no backgrounding

I don't use this app, I wasted my money on it. Buy LATENT CHAT if you want backgrounding for your LLM. This developer acts like her cares by adding useless functionality like web to RAG, but u can just download a pdf and rag that in latent chat so it does the same thing, BUT as soon as you leave this app your prompt and the response WILL ERASE WHILE STREAMING. This is not ideal for large contexts and slow LLM responses, and this guy thought he could jam in vision enabled (analyze image input) without any repercussions. So that image adding function is basically useless if you expect a long response for an LLM that utilizes your full GPU offload, and if you accidentally leave the app you can kiss your maximum effort prompt you worked on prompt bye bye! 👋

TL;DR: I see right through this gimmicky update, its not worth it until he adds backgrounding while streaming responses. Otherwise it's ok if you just need very basic text response where you are stuck inside the app and cannot leave.

😘yw for the feedback😘

🤡🤡💗🤡🤡💗🤡🤡

a year ago

Response from developer

Thank you for the feedback. I’ve recently added support for image input with LLMs that support vision, web content fetching using Jina Reader, and a new home screen widget that lets you start chats instantly with a photo, clipboard text, or a tap. The app already supports backgrounding, and I’m continuing to refine the experience in each update. I really appreciate you taking the time to share your thoughts. Just to clarify, the app is still under a year old, the “4+” label refers to the age rating, not how long it’s been around. More improvements are on the way!

No backgrounding, No image input, No web search

An app 4 years and it's still unable to do what every one of it's android competitors can? This doesn't seem legit to me at all.

GGFGGT 🤝

a year ago

Great for text! Hoping it will support all modalities in the near future!

Great for text only convos. I just wish it supported image & video input and outputs.

Dùn Èideann

a year ago

Cannot set defaults

You can’t set default instructions, skip the setup and use the server-side system prompt, or choose a default model. There’s no way to lock in default settings like temperature, context window, or streaming mode. Way too limited for power users.

inaiiantion

a year ago

Response from developer

Hi there, you can set default connection and model from the connections list. Simply swipe on the connection you would like to setup as default and it will be used by default for new chats and also for auto renaming your chat messages.

Excellent app, excellent customer support

I had problems at first, developer responded and fixed it asap. Impressive! The app is exactly what I wanted. Highly recommend. Thanks!!

Update April 17, 2025: this app is wonderful. I use it to connect to LLM’s on my Mac mini. Dev is putting out updates weekly, adding a lot of features. Wow. Very impressed!

Frugala

a year ago

Response from developer

Hi there, we released a fix for this today. Please update and give it another try.

Timeouts make it unusable for me

I use this with a Llama 70b model with Ollama server, which can respond slowly but that's fine for my purposes... after a couple of initial successful LLM text responses I start receiving "LLM is running slowly..." errors. It never recovers. The problem is persistent. The app will get better and better, but for now the timeout issue makes it unusable.

AeroD

a year ago

Response from developer

Thank you for your review and for sharing this issue. The app is designed to work smoothly with 70B models, so this behavior isn’t expected. The “LLM is running slowly” message appears if a response takes longer than 15 seconds to begin streaming — but it should not persist indefinitely. I’ll be looking into this right away to see if there’s a bug causing the message to appear incorrectly or fail to recover. I appreciate you bringing it to my attention, and I’ll work on improving the experience.

Fantastic app and great dev

I use this app daily for the integration with LM Studio in which I can host my own LLM's in LM Studio and then access them via this app on my cell or iPad for chat capabilities, which works perfectly. Also I have given several suggestions to the Dev and he always is very responsive and dedicated to making this app the most useful it can be by adding additional features.

Jameshop

a year ago

Awesome

Love this app, the keyboard is great.
I think its great thats its one price and not another subscription.

The chats just needs RAG and web search and also live camera OCR and image gen would be nice. I would gladly pay for these as in-app add-ons

tjbklyn

a year ago

Promising app, has issues

I use this with a Llama 70bodel, and after a couple of responses start receiving "LLM is running slowly..." errors. It never recovers, and the problem is persistent. Responsive developer, this app will get better and better.

AeroD

a year ago