OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Local & Self-hosted AI

Open LLM Webui

Open LLM Webui is an Apache-2.0-licensed Python application that runs relatively compact, locally operated language models through a browser interface. It supports prompt-based chat and model-specific controls across Transformers, llama.cpp and LLaVA tabs.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Open LLM Webui — OpenViST project profile in Local & Self-hosted AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to operate a supported language model on your own machine and interact with it through a local browser interface.

Who it is for

  • People who want a browser-based chat interface for language models running locally.
  • Developers and model experimenters who want to adjust generation settings or try listed model variants.

Documented uses

  • Download a listed model through the interface.
  • Send prompts and adjust generation parameters.
  • Clear chat history.
  • Upload an image and ask a related question in the LLaVA tab.
  • Add model repository paths to the model list.
Before you choose

Requirements & limits

  • The documented baseline setup uses Python 3.10, Conda and dependencies installed from requirements.txt.
  • CUDA setup is optional and has separate instructions for Windows and Linux; macOS has a documented non-CUDA path.
  • The README identifies a Mac error when running LLaVA.
  • Model examples include Phi-4-mini-instruct, Gemma 3 4B IT, Qwen 2.5 variants and others.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and launch the local web interface

Set up the application in a Python 3.10 Conda environment and open its local browser interface.

Before you start

  • Conda and Python 3.10
  • Git
  • A local machine capable of running the chosen model

Steps

  1. Create and activate a Conda environment with Python 3.10.

  2. Clone the repository and change into its directory.

  3. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  4. Run the command below and open http://127.0.0.1:7860/ in a browser.

    Documented command
    python ollm_app.py

Expected outcome

The application is launched locally and its web interface is available at the documented address.

Guide limitations

  • The README provides separate platform-specific dependency instructions for CUDA systems and macOS.
  • The README notes that running LLaVA on Mac results in an error.
Documentation 1 ↗
Source-based practical guide

Download a model and start a chat

Use the interface to obtain a listed model and submit a prompt.

Before you start

  • The application launched locally
  • A model listed in the interface

Steps

  1. Select the “Download model” button beside the model ID and wait for the download to complete.

  2. Enter a message in the “Input text” box and adjust “Max new tokens” if needed.

  3. Optionally change temperature, top-k, top-p or repetition penalty under “Advanced options.”

  4. Press Enter or select “Generate” to submit the prompt.

Expected outcome

The selected model is downloaded through the interface and can be used to generate a response to a prompt.

Guide limitations

  • The README notes that a cloud-based model update may cause a download upon execution.
  • The instructions do not establish performance for a particular computer or model.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
Uminosachi/open-llm-webui · Official homepage title · retained in its source language
How we review sourcesSuggest a correction