imp

Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faste

What is imp?

Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/kekzlimp.svg)](https://yunodb.com/tools/kekzlimp?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/kekzlimp?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/kekzlimp.svg" alt="Featured on YunoDB" height="20"></a>