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

LocalChat

LocalChat is an open-source desktop application that provides a chat interface for generative language models running on a user's computer. The documented setup uses GGUF model files and the project is built on llama.cpp.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LocalChat — 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 LocalChat when you want a conversational interface for a language model on your computer and are prepared to download a model file and account for its hardware demands.

Who it is for

  • People who want to chat with language models running on their own computer.
  • Users who want to try local models without setting up PyTorch and Transformers themselves.

Documented uses

  • Install a desktop chat interface and add a GGUF model.
  • Create conversations, send prompts, and review generated responses.
  • Keep conversation history across app restarts.
Before you choose

Requirements & limits

The repository provides releases for macOS, Windows, and Linux. The project is open source under GPL-3.0.

  • The app requires a model file downloaded separately in GGUF format.
  • Model size, quantization, and computer hardware affect speed and feasibility.
  • Conversations and chats persist across app restarts, and the model for a conversation can be changed.
  • The project warns that model outputs can contain false information, faulty calculations, or unsafe code.

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

Set up a local model for chatting

Install LocalChat and add a GGUF model file to prepare the app for conversation.

Before you start

  • A computer capable of running the app and chosen model
  • A GGUF-format model downloaded from Hugging Face

Steps

  1. Download and install the app from the repository's releases.

  2. Open the model manager for instructions.

  3. Download a GGUF-format model from Hugging Face.

  4. Place the model file in the app's model directory.

Expected outcome

The model is available for use in LocalChat conversations.

Guide limitations

  • Hardware determines which models can run and how quickly they generate responses.
  • The project estimates regular-sized models may need a dedicated GPU with 6–18 GB of video memory for responsive generation; quantized or smaller models may reduce requirements.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
nathanlesage/local-chat · Official homepage title · retained in its source language
How we review sourcesSuggest a correction