Back to News

Qwen 3.8 Flash Next (125B) Runs on RTX 4090 at 100 Tokens/s

909 points · 408 comments#qwen#llm#consumer-hardware#rtx-4090

A Hacker News post reports running Qwen 3.8 Flash Next, a 125B-parameter model, on consumer hardware (an RTX 4090) at 100 tokens per second. The post appears to be a hands-on engineering write-up, though details of the optimization techniques are not provided in the source.

Coverage timeline

  1. Hacker Newssnehesht
    Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/sHN