ChattyPage

Localai

Unrated

Lightweight, memory-efficient desktop app for running large language models locally without GPU using CPU-based quantized inference.

Chat With RTX

Unrated

NVIDIA's desktop app that lets you create a personalized ChatGPT-like AI trained on your own documents, videos, and notes.

Ollama

4.2

Run open-source LLMs locally on your machine. Simple CLI to download and run Llama, Mistral, Gemma, and other models with no setup.

LMStudio

Unrated

Desktop application for discovering, downloading, and running open-source language models locally without internet.

AskManyAI

Unrated

Chrome extension providing website summaries from multiple AI models (ChatGPT, Gemini, Llama) in a single click.

vLLM

4.7

High-throughput LLM inference engine with PagedAttention for efficient memory management. The fastest open-source LLM serving solution.