LLM Studio Go

Make room for AI that runs on your device. LLM Studio brings local language models, image generation, rich conversations and a code workspace to Android.

YOUR MODELS, YOUR CHOICE

Browse models grouped by family, including Qwen, Gemma, LFM and Bonsai, or open a compatible GGUF file from your phone. Keep downloaded models in a folder you choose. Model availability, size and hardware requirements vary.

A CHAT BUILT FOR IDEAS

Write, learn and explore with local models. Read Markdown, tables, formulas and highlighted code. Organize conversations with folders, search and pins. Attach images and open them in a full-screen viewer; image understanding requires a compatible vision model and its companion files.

CREATE IMAGES ON YOUR DEVICE

Download a supported image model and generate images locally from text prompts. View your results in image history. Generation speed and supported settings depend on your device and available memory.

MEASURE MODEL PERFORMANCE

Run built-in benchmarks for installed text and image models. Compare load time, text generation speed and image generation time, and keep results on your device.

FROM CODE TO PREVIEW

Run supported JavaScript and Python snippets in the built-in offline environment. Open supported HTML, CSS and JavaScript projects as interactive web previews directly from a response. This is a browser-based sandbox, not a server or a full desktop development environment. Python availability depends on your Android WebView.

CONTROL YOUR LOCAL RUNTIME

Adjust generation settings from the model picker, including temperature, context size and reasoning for supported models.

Choose CPU or supported GPU and NPU options, or use automatic backend selection. Availability and performance depend on the device, drivers, model and available memory. CPU remains the compatibility option.

ON-DEVICE CONVERSATIONS

Local inference does not require a LLM Studio account or a cloud AI service. Chats, attachments and generated images stay on your device unless you choose to share them. Internet access is used for model downloads, advertising and optional AI-response reports. A report sends the selected reason and optional note; the response text is included only if you choose to attach it.

The app is free and contains advertising in the model catalog and model selection menu. Google AdMob processes advertising-related device and interaction data; local prompts, chats and generated images are not sent to the advertising SDK. Privacy choices are available in settings where applicable. An optional in-app purchase removes ads.

The interface supports English, Ukrainian, Russian and nine other languages.

Before you start: download or import a compatible model. Models can occupy several gigabytes, and larger models require more RAM. AI output may be inaccurate; verify important information. This is a general-purpose AI tool, not a medical, financial or legal advisory service.

Privacy policy: https://vans.wtf/llm-studio/privacy.html

Contact: [email protected]