Open SourceOct 4, 2026 · 19:51

Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

From github.com

Image: github.com
AI;DR

Qwen3.8-Flash-Next (125B) can run on consumer hardware such as an RTX 4090 at 100T/s using the Strata inference engine, with one-click installation for Windows and Linux and support for OpenAI/Anthropic API on localhost.

Read the sourceSign in to suggest

Sources

+ 1 more
  1. DISCUSSIONsneheshtnews.ycombinator.com

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today