# Noema: Local AI & Offline LLM — Private On-Device Chat & RAG

> Offline AI language models with document integration and dataset support. (iPhone/iPad app by Alexandru Stamate.)

- Source: https://appshunter.io/ios/app/noema-local-ai-and-offline-llm/id6751169935 (this page in markdown: same URL + `.md`)
- Developer: [Alexandru Stamate](https://appshunter.io/developer/1833786674)
- Category: Productivity, Utilities
- Price: Free
- Rating: 4.50/5 from 25 App Store ratings · 11 written reviews indexed
- Age rating: 12+
- Requires: iOS 18 · 346 MB
- Languages: American English, Arabic, French (France), German (Germany), Hindi, Japanese, Korean, Romanian, Chinese (Simplified, China), European Spanish and 1 more
- Released: 2025-09-19
- Data updated: 2026-08-25
- Monetization: free
- User reviews in markdown: https://appshunter.io/ios/app/noema-local-ai-and-offline-llm/id6751169935/reviews.md

## What is Noema?

Noema brings large language model intelligence to all your devices, fully offline. Download lightweight models directly from Hugging Face, connect supported remote endpoints, and pair models with curated textbooks and your own PDFs or EPUBs. The privacy-first design means your data never leaves your device when running locally, whether you are on iPhone, Mac, or visionOS.

- Native macOS app: Run the full Noema experience on your desktop with a rebuilt interface that feels at home on macOS.
- visionOS support: Use Noema in spatial computing environments, with windows you can place around your workspace.
- Noema Relay: Connect your iPhone to your Mac via CloudKit, with no local Wi-Fi required, so one device can host a model while another becomes the client.
- Vision support for models: Attach photographs to your prompts and use multimodal models for on-device image understanding and analysis.
- Open Textbook Library integration: Browse and import entire textbooks through the built-in Explore view; Noema indexes them locally so you can search and retrieve relevant passages on demand.
- Bring your own data: Add personal documents in PDF or EPUB formats, which are embedded and indexed on-device to power retrieval-augmented generation.
- Integrated Hugging Face search: Discover and install quantized models from the Hugging Face Hub with one-tap installation, automatic dependency management, and real-time download progress.
- Remote model support: Connect to supported remote endpoints including OpenRouter and LM Studio, with updated LM Studio REST v1 compatibility and a smoother model download flow through Explore.
- Expanded model runtime support: Run models across GGUF, MLX, ExecuTorch, CoreML, and Apple Foundation Model support, giving you flexible on-device options across Apple hardware.
- RAM check and model size helper: A built-in advisor estimates each model’s memory footprint and shows when it fits your device’s budget; it can also estimate the maximum context length that fits in RAM.
- Advanced settings for power users: Fine-tune context length, quantization, and GPU acceleration; enable tool calling for built-in search and other functions; and customize model parameters for optimal performance.
- Built-in tool calling and Python support: Use integrated tools, including Python, to extend model capabilities for more advanced workflows.
- Built-in search and RAG: Use integrated search tools and retrieval-augmented generation to query your data without hitting context limits.
- Localization upgrades: Experience Noema in 10 languages, so international teams can work in the interface that suits them best.
- Private and offline by default: Local models run entirely on-device, and your conversations and files stay on your device unless you choose to use a connected remote provider.

## Key features

- Offline AI model execution
- Download models from Hugging Face
- Integrate personal PDFs and EPUBs
- Access curated textbook libraries
- Multimodal support for image analysis
- Native macOS and visionOS apps
- Remote model endpoint connection

## Recent user reviews (10 of 11)

All indexed reviews: https://appshunter.io/ios/app/noema-local-ai-and-offline-llm/id6751169935/reviews.md

### 5/5 — Works perfectly if you know what you’re doing

*2026-08-21*

This app is a hidden gem and must maintain its superiority. It is 100% better than LM Studio in my humble opinion. If a user doesn’t like it, its because they don’t know how to use it properly.

**Developer response:** Thank you for review! We'll continue improving Noema on Mac, if you have any feature you'd want to see specifically, feel free to email clientcare@noemaai.com.

### 5/5 — Very good free AI

*2026-08-17*

It's basically LMStudio for iOS. Does lightweight tasts very well and replicates gpt mini or gemini flash

**Developer response:** Thanks for your review! We appreciate the support.

### 2/5 — Very bad

*2026-08-09*

Ok, so that’s very bad, there is ALWAYS a ~300 token context allocation on “tools” which I simply cannot turn off

**Developer response:** Hi there, thanks for your review. We have fixed your issue and will push an update in the next few days. Please try Noema again and update your review if your issue is resolved. If you encounter any more issues, you can also always email us at clientcare@noemaai.com.

### 5/5 — Great App

*2026-07-22*

This is a great tool to learn and play with. I appreciate that the developer frequently releases updates to add features or to address specific user requests.

**Developer response:** Thank you so much for the thoughtful review. I’m glad you’re enjoying exploring and learning with Noema. User feedback plays a large role in shaping each update, so it means a great deal to hear that the improvements have been useful.

### 4/5 — Off-grid mode works

*2026-04-25*

The latest update fixed the off-grid.

**Developer response:** Update: Hi xxxsman, the issue you were encountering has been fixed, please let us know if you continue encountering issues.

Hi there xxxsman! We're sorry the off-grid functionality is not working correctly. We have a team of early testers and thoroughly test features before we release, this is actually a feature that has been in Noema for a long time. We'd love if you could send us an email at clientcare@noemaai.com as this might be a device-specific bug. Please contact us and we'll fix this as soon as possible.

Thank you.

### 2/5 — Not working after 2.0 update

*2026-03-10*

After updating to 2.0, I cannot load any model regardless of the size or quantization.
Please update the application to resolve the issue.

Load Failed
Failed to start loopback Ilama.cpp server for this GGUF model.

**Developer response:** Hi Paul,
Please update the app to version 2.1 as we have tried to fix the bug you mentioned. Please email us or update your review to let us know if the problem has been fixed. Thank you.

### 5/5 — Best offline LLM solution on iOS

*2025-12-13*

Really, this is exactly the kind of offline LLM experience that I am looking for on iOS. Bravo! There were some minor bugs here and there, but the core experience works greatly. If iOS can relax the memory limit a bit more I am sure the app could get much more useful with larger models but one could dream at this moment. Still, the app itself really stands out. I am wondering if there’s a way to support the developer…

**Developer response:** Hi, thanks for your review! We’re working towards resolving all the bugs and improving the overall user experience so that it is closer to what you could find on desktop. Thanks for again for your support! At the current time, there’s no way to support, but in future releases I will look into it. Your feedback currently is more than enough!

### 5/5 — Neat app

*2025-11-23*

Interesting local LLM app. I like what you have done and hope you keep expanding on it.  Lots of great ideas here

### 5/5 — Great App

*2025-10-07*

Noema is the most reliable on-device AI I’ve tried. It runs locally on my iPhone, so responses are fast and my data stays on my device. I can bring in my own documents and get answers based off them. Clean UI, and the app id clearly optimized for iOS. Easily a daily tool for work or study.

### 5/5 — The best so far

*2025-10-06*

I’ve tried all the apps for local AI and for accessing a remote backend and this is the best so far. It’s professionally designed and implemented, offers free search and RAG (ability to interact with documents), has both recommended local models and search for downloadable models, and at this writing is free. The developer has been very responsive to suggested improvements. Deeply grateful to the developer for the time and effort to create and polish this gem!

**Developer response:** Thanks for your review. It means a lot to me. If you need anything else regarding the features Noema offers, don't hesitate to reach out again!

## Frequently asked questions about Noema

### Does NoemaAI have ads?

NoemaAI is ad-free. The application is free to download and use, with no advertisements displayed to users.

### What devices does NoemaAI support?

NoemaAI is available on Mac, iPhone, iPad, and visionOS devices, offering a consistent experience across Apple's ecosystem.

### How does NoemaAI handle user data privacy?

NoemaAI prioritizes privacy by running models entirely on-device when used locally. Your conversations and files remain on your device unless you opt to use a connected remote provider.

### Can I use my own documents with NoemaAI?

Yes, you can add personal documents in PDF or EPUB formats. NoemaAI embeds and indexes these documents on-device to power retrieval-augmented generation.

### How often is NoemaAI updated?

The latest version of NoemaAI is 2.1, with the last update on March 27, 2026. Updates typically include new features, performance improvements, and expanded model support.

### What is the age rating for NoemaAI?

NoemaAI has an age rating of 12+, making it suitable for users aged 12 and above.

### Can I connect NoemaAI to remote AI models?

Yes, NoemaAI supports connecting to supported remote endpoints such as OpenRouter and LM Studio, allowing you to leverage external models.

### What are the benefits of the Open Textbook Library integration?

The Open Textbook Library integration allows you to browse and import entire textbooks directly into NoemaAI. These are then indexed locally, enabling you to search and retrieve relevant passages on demand.

## Version history (last 5 releases)

### 3.7 — 2026-08-19

• Python code execution: models can now write and run real Python on your device, entirely offline. Ask for a calculation, a statistical summary, or a reshaping of your own data, and Noema runs the code and shows you the result next to it.
• A scientific toolkit is bundled inside the app — NumPy, pandas, SciPy, scikit-learn, SymPy, Matplotlib, and more — so data analysis, statistics, symbolic math, and machine learning work with no network and nothing to install. The packages ship with Noema and cannot be added at runtime.
• Charts arrive in the conversation. Matplotlib figures are drawn inline, and a separate Quick Charts tool renders native bar, line, scatter, and pie charts from data a model has already prepared, without running any Python.
• Tap a chart to open it full size, zoom in, and share or save it.
• Execution is deliberately confined: no network access, no subprocesses, no loading of outside libraries, a temporary working directory it cannot leave, and a 30-second limit on every run.
• Turn Python on in Settings under Tools, then arm it from the + menu in a chat. A new Python page lists the runtime version, every bundled package with its version and dependencies, and the health of the package set.
• Code blocks inside a model's reasoning keep their formatting instead of being flattened, and images in tool results are sized correctly in the viewer.
• Short conversations no longer jump while a reply is streaming in, and the first suggested message hands off to the chat more smoothly.
• Interface fixes, bug fixes, and polish throughout.

### 3.6.1 — 2026-07-29

• Constellation: use your Mac's models from your iPhone, iPad, or Vision Pro. Any Mac on your iCloud account with Remote Access turned on is found on its own — no address or token to enter — and tapping Use opens the chat right away while the Mac loads in the background.
• Noema picks the most private way to reach your Mac for each message, from your local network through to an encrypted relay, and shows which one it is using in the chat header. Off-grid Mode now holds across every kind of connection, not just ordinary web traffic.
• Your Mac can stand in for the cloud: its models appear in Autopilot's Stronger Model picker, and a new Fallback Model means a hard question tries another model before your on-device one answers.
• Chats sync across your Apple devices if you want them to — one switch, off by default, in a new Sync & Devices setting. Conversations, bookmarks, and per-chat settings travel through your private iCloud account, and a reply that finishes on your Mac appears on your phone without opening the app.
• Projects group related chats under shared instructions and sources, so every conversation in a project starts from the same context. Import PDFs, EPUBs, and text files straight into a project, or attach datasets you already have.
• A rebuilt chat drawer brings search, projects, bookmarks, favorites, and date groups into one list with a preview of the last reply on every row, and chats stay noticeably faster during long generations.
• Images you attach now reach the model at full resolution instead of being shrunk on the way in, so screenshots, receipts, and dense charts are legible to it for the first time.
• Paged Overfit models run with the context you choose instead of a hidden cap, and Laguna S 2.1 now works as a Paged model.
• Models are more honest about what they can do: a vision model that cannot actually read images no longer claims it can, and downloaded models use the Chat Template they shipped with.
• On Mac, the Relay page is replaced by a simpler Developer page, and Remote Access has moved into Settings, under Sync & Devices.
• Interface fixes, bug fixes, and polish throughout.

### 3.6 — 2026-07-28

• Constellation: use your Mac's models from your iPhone, iPad, or Vision Pro. Any Mac on your iCloud account with Remote Access turned on is found on its own — no address or token to enter — and tapping Use opens the chat right away while the Mac loads in the background.
• Noema picks the most private way to reach your Mac for each message, from your local network through to an encrypted relay, and shows which one it is using in the chat header. Off-grid Mode now holds across every kind of connection, not just ordinary web traffic.
• Your Mac can stand in for the cloud: its models appear in Autopilot's Stronger Model picker, and a new Fallback Model means a hard question tries another model before your on-device one answers.
• Chats sync across your Apple devices if you want them to — one switch, off by default, in a new Sync & Devices setting. Conversations, bookmarks, and per-chat settings travel through your private iCloud account, and a reply that finishes on your Mac appears on your phone without opening the app.
• Projects group related chats under shared instructions and sources, so every conversation in a project starts from the same context. Import PDFs, EPUBs, and text files straight into a project, or attach datasets you already have.
• A rebuilt chat drawer brings search, projects, bookmarks, favorites, and date groups into one list with a preview of the last reply on every row, and chats stay noticeably faster during long generations.
• Images you attach now reach the model at full resolution instead of being shrunk on the way in, so screenshots, receipts, and dense charts are legible to it for the first time.
• Paged Overfit models run with the context you choose instead of a hidden cap, and Laguna S 2.1 now works as a Paged model.
• Models are more honest about what they can do: a vision model that cannot actually read images no longer claims it can, and downloaded models use the Chat Template they shipped with.
• On Mac, the Relay page is replaced by a simpler Developer page, and Remote Access has moved into Settings, under Sync & Devices.
• Interface fixes, bug fixes, and polish throughout.

### 3.5 — 2026-07-21

• Noema Overfit (experimental): run models far larger than your device's memory would normally allow — even 100B-class models on a laptop — by streaming their experts from storage on demand. This is early and evolving, so expect rough edges.
• PDF attachment parity: attach and read PDFs the same way across iPhone, iPad, and Mac, with consistent inline indexing everywhere.
• Longer conversations that don't stall: new context compaction keeps chats going smoothly as they grow, so Noema stays responsive deep into a thread.
• Fixed a model that could still appear loaded after it had actually been unloaded — for example when the app closed or the model was ejected unintentionally.
• Fixed the key/value cache occasionally disappearing during a session.
• Interface fixes, bug fixes, and polish throughout.

### 3.4 — 2026-07-17

• Attach documents to chat on iPhone and iPad: add PDFs, EPUBs, and text files from the Files app and watch them index inline, so answers can draw on them right away.
• Redesigned chat status drawer: compact capability controls, reasoning and Autopilot status, MCP visibility, and a clearer, more detailed context-budget meter.
• Steadier iCloud sync across your devices.
• Tidier model settings: a faster GGUF screen, with vision options shown only for models that support them.
• Sharper math rendering for numbers and complex formulas, plus cleaner web citations.
• Fixed a model that could still appear loaded after it had been unloaded.
• Interface polish, bug fixes, and localization across every supported language.

## Apps similar to Noema

| App | Rating | Price | Category |
| --- | --- | --- | --- |
| [Arbiter - Local AI Chat](https://appshunter.io/ios/app/arbiter-local-ai-chat/id6747954532) | 4.9 (16) | Free | Productivity |
| [AI Reader: Read Aloud Pdf Book](https://appshunter.io/ios/app/ai-reader-read-aloud-pdf-book/id6754524209) | 4.7 (143) | Free | Productivity |
| [Memio AI Voice Notes & Journal](https://appshunter.io/ios/app/memio-ai-voice-notes-and-journal/id6755295146) | 4.6 (15) | Free | Productivity |
| [Local LLM: MITHRIL](https://appshunter.io/ios/app/local-llm-mithril/id6751945393) | 4.4 (13) | Free | Productivity |
| [Anywhere AI](https://appshunter.io/ios/app/anywhere-ai/id6749791800) | — | Free | Productivity |
| [VisualGPT - Offline AI](https://appshunter.io/ios/app/visualgpt-offline-ai/id6747297611) | — | Free | Productivity |

## Related topics

[noemaai](https://appshunter.io/ios/topics/noemaai) · [noema](https://appshunter.io/ios/topics/noema) · [gldm](https://appshunter.io/ios/topics/gldm) · [rfsm](https://appshunter.io/ios/topics/rfsm) · [otherside cli](https://appshunter.io/ios/topics/otherside-cli) · [peterjohn pytorch mps](https://appshunter.io/ios/topics/peterjohn-pytorch-mps) · [ialtair](https://appshunter.io/ios/topics/ialtair)

---

*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 2026-08-25.*