OfflineGPT

CodeAlp

In-app purchases

About this app

OfflineGPT brings powerful AI directly to your device — no internet, no cloud, no account required. Chat with state-of-the-art language models, generate images locally, and keep full control over your data.

Why OfflineGPT:
- Full privacy: your data never leaves your device
- Works completely offline (travel, flights, restricted networks)
- One-time purchase, optional Pro upgrade
- No subscriptions

Important to know:
- OfflineGPT is not a cloud AI replacement
- Responses are slower than cloud AI (device-dependent)
- Performance depends heavily on device hardware
- Best experience on modern phones
- If you expect instant cloud-level responses, this app is not for you

Use cases:
- Offline notes and writing
- Brainstorming and drafts
- Private AI without internet access

Device requirements:
- Android 10 minimum (Android 12+ recommended)
- Minimum 4 GB RAM (6–8 GB recommended)
- ARM64 CPU (Snapdragon 6xx / 7xx / 8xx recommended)
- Models require ~1–2 GB storage each (download once)

How it works:
- Install the app (~100 MB)
- Download an AI model (one-time)
- Chat offline – no setup, no account

Pro upgrade (optional):
- Larger memory
- Custom system prompts
- Personalization features
- Multiple models and AI tools
No subscription. One-time purchase.

Model licenses:

OfflineGPT uses open-weight models running locally on your device.
No server communication is involved.

Text models:
- LFM 2.5 – Apache 2.0
https://huggingface.co/LiquidAI
- Llama 3.2-1B-Instruct – Llama 3.2 Community License
https://www.llama.com/llama3/
- Qwen 3 Thinking Models – Apache 2.0
https://github.com/QwenLM/Qwen3
- Qwen 2.5 Models – Tongyi Qianwen License
https://github.com/QwenLM/Qwen/blob/main/LICENSE
- Gemma – Google Gemma Terms
https://ai.google.dev/gemma/terms
- Rocket-3B – CC BY-SA 4.0
https://creativecommons.org/licenses/by-sa/4.0/

Image models:
- AbsoluteReality – CreativeML Open RAIL-M
https://huggingface.co/Lykon/AbsoluteReality
- Anything v5 – CreativeML Open RAIL-M
https://huggingface.co/stablediffusionapi/anything-v5

All models are used in accordance with their licenses.
Some image models are converted to MNN format for efficient on-device inference.
Model weights are not modified beyond format conversion.

Ratings and reviews

I haven't actually tried it yet, but I downloaded it, and it's like downloading two gigabytes of data, which is probably all of the information that it uses. It should be more than efficient on a modern device, especially with an NPU and a high-powered processor. All the negative reviews are probably from people who don't have the most recent phones, phones that don't have NPUs. On the S25 Plus, with a 4.5 GHz processor, a GPU, and an NPU, replay started 1 -1.5 seconds VERY FAST!! SLOW

Not sure why this app has so few downloads and reviews so far, but it's one of the best offline ai's I've used. It runs smooth as butter on my device. It has so many options, features, and models to choose from. Upgrading to premium is optional, the app still works great without it. The upgrade is a one time purchase and pretty cheap at around $12 USD. The features you get from premium are more than worth it I'd say.

Love the UI and the whole concept. There's room for improvement though. It's slow in comparison to Layla, PocketPal and MNN Chat (though it looks way better). Larger models don't work (if you've got a 16GB phone) and you can't change hardware acceleration CPU/GPU/NPU (yet). AI Tools are really nice and I cannot recommend enough the visuals. Great start. Bought the Pro version. Well done, devs.

What’s new

Important update: The download link for the Gemma 4 LiteRT model has been updated. This fixes an issue where the model could not be loaded correctly.

Thai has also been added as a new language.