Kimi-K3 Releases on HuggingFace 7/27

Kimi-K3于7月27日在HuggingFace发布

HN 459 分 · 207 条评论 · 作者 nateb2022 · 来源 huggingface.co · HN 讨论

【摘要】

原文抓取失败，摘要暂不可用，请访问原文链接。

【评论】共 225 条 · 按 HN 热度顺序 · 楼中楼缩进展示

1L @NitpickLawyer · 2026-07-27 14:37

This will be interesting for a few reasons. First, depending on where the median pricing settles w/ 3rd party providers will tell us what it costs to serve a 3T model. Since it's going to be mxfp4 native, it'll take ~1.5TB of VRAM to host this, which is juuust at the limit of 8xb200s (but realistically you'll need 16x for context / throughput optimisation). Won't be cheap to host, but at least we should get some range of $/MTok for a 3T model. Then we'll be able to guesstimate if "labs are subsidising tokens on API pricing".

⋯ 继续阅读请登录会员 ⋯