← AI tools directory

Self-hosted · LLM / chat

vLLM

High-throughput open-source LLM serving engine for your own GPUs.

Best for: Self-hosted multi-user model serving

Pricing: Free (OSS) + hardware

Official site All tools

Strengths

Serious throughput
OpenAI-compatible server
Industry default for many stacks

Watch-outs

Needs real GPU ops skill
Not a chat UI by itself

Appears in these stacks

Local / offline AI · supporting — When you have real GPUs and multi-user load.