DeepSeek V4 Flash at 278 tok/s, full precision, no quantization | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

DeepSeek V4 Flash at 278 tok/s, full precision, no quantization(runinfra.ai)

5 points by OsamaJaber 11 hours ago | 3 comments

DeepSeek V4 Flash at 278 tok/s, full precision, no quantization | Dark Hacker News

literallyroy 42 minutes ago |

I don’t see RunInfra as a provider on OpenRouter. Why not?

sscaryterry 10 hours ago |

If this is accurate, this can be a game changer...

OsamaJaber 5 hours ago | |

you can give it a try