Lollms WebUI
Local LLM web interface for Windows, macOS and Linux. Use GGUF models, Ollama or cloud APIs, with local chat storage and an Apache 2.0 license.
Lollms WebUI is a local, single-user AI interface for people who want text chat and media generation in one place. It runs on Windows, macOS and Linux, with Docker support, and lets writers, developers and other users choose models and task-specific personalities. It's free and open source under Apache 2.0. The project receives minimal maintenance.
Its model support spans Hugging Face models, GGUF/GGML and ExLlamaV2, plus connections to Ollama and vLLM. You can also use cloud services such as OpenAI, Anthropic and OpenRouter. The interface runs locally and stores discussions in a local database; cloud-backed requests go to the selected provider.
Beyond writing and code assistance, it supports image analysis and image generation through Stable Diffusion, Flux and ComfyUI, as well as hosted services such as DALL-E and Midjourney. Video generation connects to tools including CogVideoX and RunwayML, while MusicGen handles music generation. Available capabilities depend on the models and services you choose.
Smart Routing selects models according to prompt complexity, with priorities for response speed or service cost. Task-specific personalities provide preset behavior for different kinds of work. You can search and export discussions, edit messages and rate answers.
The WebUI has no built-in user authentication and is intended for local use. Its headless mode exposes the generation API without the full web interface.
