Local LLM vs DFM Mimir
Price, ratings, monetisation and update history for both apps, side by side — with what reviewers say about each.
Local LLM
This app allows you to run advanced AI language models directly on your iPhone, offering offline chat, photo analysis, and document interaction. Create websites, interactive pages, and games through conversation, with features varying by the chosen model.
- Offline AI language model execution
- On-device chat and photo analysis
- Document interaction and PDF support
- AI-powered website and game creation
- Live voice input
- Model catalog for downloads
Read full descriptionHide full description
Local LLM runs language models on your iPhone. No account is required. Chat, ask about photos, work with documents and use live voice. With Canvas, build websites, interactive pages and games from a conversation, then preview and edit them in the app. Features depend on the selected model. Download models from the catalog, or use Apple’s on-device model on supported devices when available. Core AI models require iOS 27 or later. Other supported models remain available on older systems. Inference and conversation history stay on your device. Model downloads, the catalog and model artwork use the network. Optional Web Search sends a query derived from your message to Tavily and may read result websites. Weather requests use Apple geocoding and WeatherKit for the requested city, without requesting device location. Voice input prefers on-device recognition. If it is unavailable or fails, Apple’s online speech service may process audio when network speech recognition is enabled. You can disable this in Privacy settings. Requires iOS 17 or later. Model availability depends on your device, OS, memory and storage. Downloads require internet; supported offline chat works after setup. Models can make mistakes. Do not rely on replies for medical, legal or financial decisions.
DFM Mimir
Read full descriptionHide full description
Chat with Mimir locally on your device without anything being sent out (unless you want to). Mimir is a frontier language model from Danish Foundation Models, a research collaboration across the University of Southern Denmark, Aarhus University, Copenhagen University, and the Alexandra Institute. Mimir was trained on SDU UCloud. The app includes a pre-packaged DFM Mimir v1.5 in a compact 4-bit format. The model runs on your device, so you can start chatting without an account or an additional model download. Ordinary chats work offline and are stored locally. • Write, rewrite, brainstorm and ask questions in Danish or English. • Keep multiple conversations and read answers with basic Markdown formatting. • Adjust text size, reply length, context size and generation settings. • Summarize earlier conversation turns to make room in longer chats, with an option to see the summary as it is generated. • Use the bundled model or manage compatible Mimir GGUF models. Optional online features are controlled in Settings. Model discovery/downloads contact Hugging Face and the catalog host. Web search requires a Mimir search key and sends search queries when activated. Sharing feedback asks for confirmation before sending the current chat; permission to publish feedback under CC BY 4.0 is a separate choice. Mimir can make mistakes. Check important answers. Speed and usable context size depend on your device and available memory. The included model was trained with a context length of 4,096 tokens; larger settings are experimental. The bundled model makes this a large download (about 1 GB including model weights). Runs locally on compatible iPhone and iPad devices, as well as Mac computers, using Apple Metal acceleration where available. Large contexts and simultaneous apps can increase memory pressure; choose smaller settings on devices with less available memory.
Screenshots
Verdict
Local LLM and DFM Mimir are too close to call on the numbers: across 5 compared parameters — price, ads, in-app purchases and device support among them — neither pulls far enough ahead to decide it. What separates them is feature set and interface, not measurable difference.
Scored on Price · Rating · Positive reviews · Number of ratings · Update frequency · Ads · In-app purchases · Monetization · Best chart rank · Devices · Requires iOS
Both are free to download. Neither carries in-app purchases, so what you see is what you pay.
| Parameter | Local LLM | DFM Mimir |
|---|---|---|
| Price | Free | Free |
| Rating | 4.6 (9 ratings) — better | — |
| Positive reviews | 100.0% of reviews | — |
| Number of ratings | 9 — better | — |
| Update frequency | Every 3 days | — |
| Ads | No | No |
| In-app purchases | No | No |
| Monetization | Free | — |
| Devices | iPhone | iPhone, iPad — better |
| Requires iOS | 17.0 | 17.0 |
| Further details — not scored | ||
| Size | 99 MB | 1.1 GB |
| Age rating | 12+ | 12+ |
| Developer | Yanchen Zhao | Syddansk Universitet |
In-app purchases
Local LLM
No in-app purchases
DFM Mimir
No in-app purchases









