Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s(github.com)
892 points by snehesht | 402 comments
GitHub repository for Strata, an inference engine offering one-click install to run Qwen3.8-Flash-Next locally on consumer hardware with an OpenAI/Anthropic-compatible API.

























![Screenshot of youtube.com: How to scale intent, quality, and artistry with AI [video]](https://hn.urlbox.com/shots/renders/2026/10/4/19a83d9b-9696-4e42-89f7-05b0effd5404.jpg)






![Screenshot of youtube.com: Homa: The end of TCP for AI clusters [video]](https://hn.urlbox.com/shots/renders/2026/10/4/cc29e144-96cb-4fc8-a781-e61a3640372d.jpg)


























