omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon, managed from the macOS menu bar

What it costs

Free and open source

Category

Chat & Assistants

On Radar

Open-source project on GitHub, 22,883 stars

Ranks

No. 117 of 644 in Chat & Assistants

Released

13 February 2026

Website

github.com · jundot/omlx ↗

Similar AI chatbots and assistants

1. mlc-llmUniversal LLM Deployment Engine with ML Compilation★ 23,249
2. ⚡Llama 3- 70B ChatbotLlama 3 chatbot with lightning speed generation (Groq)♥ 80
3. GPT-4.5The largest and best model for chat yet in GPT family▲ 487
4. ⚡GPT OSS WebGPURun GPT-OSS-20B locally in your browser on WebGPU♥ 76
5. Ollama Desktop AppThe easiest way to chat with local AI▲ 482
6. gpt-crawlerCrawl a site to generate knowledge files to create your own custom GPT from a URL★ 22,398

Make omlx? Show it's listed on Radar

Add this badge to your site or README. It links to this page.

<a href="https://raunakpatil.com/ai-tools/tool/omlx"><img src="https://raunakpatil.com/img/badges/listed-on-radar.svg" alt="omlx is listed on Radar" height="40"></a>

[![Listed on Radar](https://raunakpatil.com/img/badges/listed-on-radar.svg)](https://raunakpatil.com/ai-tools/tool/omlx)