vMLX provides functions no other MLX inferencing app does, including LM Studio, from KV Cache Quantization (save 2-4x the RAM), Prefix Caching, and full VL support.
Cost / License
- Free
- Proprietary
Application type
Platforms
- Mac
United States


Open WebUI is described as 'Extensible offline AI platform with user-friendly interface, LLM runner support, RAG inference, privacy focus, no registration, text-to-image, cloud sync, and dark mode' and is a popular AI Chatbot in the ai tools & services category. There are more than 50 alternatives to Open WebUI for a variety of platforms, including Mac, Windows, Linux, Web-based and Self-Hosted apps. The best Open WebUI alternative is Jan.ai, which is both free and Open Source. Other great apps like Open WebUI are Ensu, AnythingLLM, LM Studio and LibreChat.
vMLX provides functions no other MLX inferencing app does, including LM Studio, from KV Cache Quantization (save 2-4x the RAM), Prefix Caching, and full VL support.


A local-first AI workspace that runs open-weight models (GGUF via llama.cpp and MLX) directly on consumer hardware with integrated MCP tool support.




Run AI models locally on your device. Foundry Local provides on-device inference with complete data privacy, no Azure subscription required.
AirmailAI is a bring-your-own-API-keys LLM chat app, with a focus on security, privacy, and performance. It uses a website frontend and browser extension backend, and conversations never touch AirmailAI servers.


Greenative Studio lets you run local LLMs with your files, tools, and coding agents - without sending sensitive data or source code to cloud AI services.



QVAC converts local AI into a high-quality experience that sits in your pocket. All the value you’re used to seeing in other AI assistants, minus the lack of privacy.




Grengin is an open-source (Apache 2.0) AI workspace that lets teams chat with OpenAI, Anthropic, Google Gemini, Mistral, Amazon Bedrock, and other models from one branded interface, without handing data control to a vendor.




Your AI, on your device. Nothing leaves it. Summarize, extract, and rewrite text with the model that lives on your iPhone, iPad, or Mac. No cloud, no accounts, no servers. Works even in airplane mode.



Polycode is a native macOS chat client for developers who use more than one AI model. It sends every prompt to each provider you configure, in parallel. A primary model reads every reply and writes one answer.




BlackCortex Lite is a free, self-hosted AI chat application that runs entirely on your machine. No cloud, no subscriptions, no data leaving your network. Built for home use — launch the exe, open a browser, and everyone on your LAN can use it immediately.




The desktop app for Ollama. Chat, code, and plan with your local models — and scale to faster cloud models when you need them. Free local use, no account required.
