Get the latest tech news

Hetzner is working on LLM Inference

Hetzner has launched an experimental LLM inference API. I tested its Qwen model—and have a few guesses about where the product could go next.

None

Related news:

PostgreSQL Benchmark: AWS RDS vs. Self-Hosted on Hetzner (2026)

DeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85%

Real-time LLM Inference on Standard GPUs: 3k tokens/s per request