3sparks Chat

Name: 3sparks Chat
Price: 5.99 USD
Rating: 4.2 (29 reviews)
Author: 3sparks Labs LLC

AI Chat Client and Keyboard

$5.99 · Designed for iPad. Not verified for macOS.

29 Ratings
Age Rating

4+
Years
Category

Productivity
Developer

3sparks Labs LLC
Language

EN
English
Size

31.7
MB

Chat smarter with 3sparks Chat – your personal LLM client for local and cloud models. Connect to your favorite AI models, whether they’re running on your own machine or through cloud services: • Local models like LM Studio, Ollama, AnythingLLM, OpenWebUI (Mac, PC, or Linux) • Cloud-based APIs like OpenAI, Mistral, Gemini and others Now with powerful new tools: • Image & file support – Upload images (for vision-capable models) or text files (supported by all models) to enhance your chats. • Web content reader – Fetch and include webpage content in your chats using Jina Reader • Home screen widget – Start a new chat instantly by snapping a photo, uploading an image, pasting clipboard text, or starting blank • Share extension – Send text or links from any app into 3S Chat with a tap Plus, the built-in AI Keyboard Extension lets you rephrase and fine-tune your writing in any app like iMessage, WhatsApp, and email: • Customizable prompts for instant rewriting • Personalized tone and style settings • No forced cloud storage – your data, your choice 3S Chat is optimized for iOS, iPadOS and VisionOS, so you can enjoy a seamless experience across your iPhone, iPad, and Apple Vision Pro.

Ratings & Reviews

4.2

out of 5

29 Ratings

Great start, but needs more features.
06/15/2025
Dùn Èideann
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.
Great start, but needs more features.
06/15/2025
Dùn Èideann

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.
Still no backgrounding
06/11/2025
🤡🤡💗🤡🤡💗🤡🤡
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😘

Developer Response
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!
Still no backgrounding
06/11/2025
🤡🤡💗🤡🤡💗🤡🤡

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😘
Developer Response 06/09/2025
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!
Exactly what I was looking for
11/18/2024
Derek WH
This is the only app of this kind that I can find for iOS to connect to an LM Studio server for local LLM chats. It connected easily, and I was able to be up and running in just a few minutes. It seems to be a bit slower than running locally, but that might have to do with the models I’m running more than the app itself. I also had some issues with garbled responses from certain models, but I have some that work perfectly so there might just be some incompatibilities somewhere in my settings. Overall it’s a great app though, and I’m always happy to see something that doesn’t require any kind of ongoing subscription.
Exactly what I was looking for
11/18/2024
Derek WH

This is the only app of this kind that I can find for iOS to connect to an LM Studio server for local LLM chats. It connected easily, and I was able to be up and running in just a few minutes. It seems to be a bit slower than running locally, but that might have to do with the models I’m running more than the app itself. I also had some issues with garbled responses from certain models, but I have some that work perfectly so there might just be some incompatibilities somewhere in my settings. Overall it’s a great app though, and I’m always happy to see something that doesn’t require any kind of ongoing subscription.
Works great with LM Studio
5d ago
Sam Gleske
I have LM Studio on a private VPN. Works great with authentication enabled in LMS. Would be nice to support compaction. e.g. I have 200k context available and compaction could open a new chat that is compacted to 30k tokens with 40k most recent tokens remembered. For example, "new" compacted chat would "start" over with 70k tokens (30k summary with 40k recent preserved as literal text from previous chat (ok to have a nonsensical cutoff). Compaction should be per-connection configurable. Per model is even better buy per connection is still great and easier to implement.
Works great with LM Studio
5d ago
Sam Gleske

I have LM Studio on a private VPN. Works great with authentication enabled in LMS. Would be nice to support compaction. e.g. I have 200k context available and compaction could open a new chat that is compacted to 30k tokens with 40k most recent tokens remembered. For example, "new" compacted chat would "start" over with 70k tokens (30k summary with 40k recent preserved as literal text from previous chat (ok to have a nonsensical cutoff). Compaction should be per-connection configurable. Per model is even better buy per connection is still great and easier to implement.

Pin the chats you use every day to the top of the list. Speak your messages with dictation, and have replies read back to you. Claude models can now think before answering, with the thinking shown separately from the reply. Start a chat or send a message from Shortcuts, Siri, or the Action button. Download any public Hugging Face model, not just the curated catalog. Paste a model ID or URL and pick the file you want. Also in this release: - Connections show their provider's logo, and every list in the app now shares one design - On iPad, Return sends and Shift+Return starts a new line - The "local model not loaded" notice can be dismissed - A connection missing its API key now says so - Timestamps no longer tick once a second Fixes: - Turning off memory for a chat now sticks - Deleting a chat's messages also clears what was remembered from them - Switching to a model that cannot reason no longer strands the setting - Sending works again as soon as you are back online - Quitting mid-save no longer loses a message

Version 3.2 Aug 30

Data Not Collected

The developer does not collect any data from this app.

Privacy practices may vary, for example, based on the features you use or your age. Learn More

Accessibility

Information

Seller: 3sparks labs llc
Size: 31.7 MB
Category: Productivity
Compatibility: Requires iOS 18.6 or later.

iPhone
Requires iOS 18.6 or later.

iPad
Requires iPadOS 18.6 or later.

Mac
Requires macOS 15.6 or later and a Mac with Apple M1 chip or later.

Apple Vision
Requires visionOS 2.0 or later.
Languages: English
Age Rating: 4+

4+

Learn More