Cohere's API documentation helps developers easily integrate natural language processing and generation into their products.
off-grid-mobile
OGAM is an offline AI app for phones and Mac with chat, vision, speech, image generation, and tool calling.

About off-grid-mobile
OGAM, also called Off Grid AI, is an open source app for phones and Mac that runs AI models on the device itself. It covers text chat with GGUF language models, image analysis, speech-to-text with Whisper, image generation with Stable Diffusion, and tool calling. The project states that it needs no account or API key and that data stays on the device.
Hardware acceleration depends on the device. The project describes GPU support on Adreno and Apple Silicon hardware, and an NPU (Hexagon) option that it labels experimental. The NPU path only accelerates Q4_0 and Q8_0 quantizations, and the project notes that some model architectures produce garbled output on it. Models that can use the GPU or NPU are marked in the model list. Models are downloaded to the device, and the project mentions downloads of about 4GB.
An optional paid Pro tier is described on the project page at $119 one-time or $7.99 per month. Pro adds on-device text-to-speech, custom personas, and drafted actions that wait for user approval. Its calendar, email, and MCP server connections involve external services, and the project's privacy statement applies to the core app rather than to those connections.
Key features
- Runs GGUF language models such as Qwen 3, Llama 3.2, and Gemma 3
- Analyzes images with on-device vision models
- Transcribes speech with Whisper speech-to-text
- Generates images using Stable Diffusion
- Connects to OpenAI-compatible servers on the local network, such as Ollama
- Uses GPU or NPU acceleration where the device supports it
- Requires no account or API key, according to the project
- Open source, with the code available in a public repository
- Detects available GPU and CPU options and defaults to the fastest working backend, which can be overridden in Settings
- The NPU option is marked experimental and only accelerates Q4_0 and Q8_0 quantizations
- Some model architectures produce garbled output on the NPU, according to the project
- Models can be large, with the project citing a download of about 4GB
off-grid-mobile at a glance
- Website
- github.com/off-grid-ai/OGAM
- Category
- AI & Machine Learning › AI Image Generators
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Platforms
- Android, iOS
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
off-grid-mobile alternatives
Tools and sites you could use instead, ranked by how closely they match.
Playbook stores, organizes, searches, and shares photos, videos, and design files in a collaborative media library.
SD.Next is a web interface for AI image and video generation, captioning, and processing.
Fast Stable Diffusion combines Stable Diffusion and DreamBooth in a project focused on image generation.
Stable Dreamfusion supports text to 3D and image to 3D generation, with mesh export using NeRF and diffusion.
Produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image.
Popular in AI Image Generators
Well-known listings from the same topic.
off-grid-mobile FAQ
Does Off Grid AI require an account or API key?
Can it connect to other AI servers?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












