Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s
Hacker News 热议:Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s(505 赞 / 252 评论,来源 github.com)
一句话概要
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input. - Niko1221/Strata
原文开头节选
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Niko1221 / Strata Public Notifications You must be signed in to change notification settings Fork 945 Star 10.7k main Branches Tags Go to file Code Open more actions menu Latest commit History 845 Commits 845 Commits Folders and files Name Name Last commit message Last commit date .github .github bench/ results bench/ results cmake cmake data data docs docs include/ strata include/ strata ref ref serve serve src src sycl sycl tests tests third_party/ ggml third_party/ ggml tools tools .dockerignore .dockerignore .gitattributes .gitattributes .gitignore .gitignore AGENTS.md AGENTS.md CMakeLists.txt CMakeLists.txt Dockerfile Dockerfile LICENSE LICENSE README.de.md README.de.md README.es.md README.es.md README.fr.md README.fr.md README.ja.md README.ja.md README.md README.md README.pt-BR.md README.pt-BR.md README.zh-CN.md …
(以上为原文节选,完整内容见下方”原文来源”)
这条动态今日登上 Hacker News 首页(505 赞 / 252 评论,来源 github.com)。技术雷达每日自动聚合 AI 工程、后端架构、DevOps 方向的前沿动态;相关工程落地可浏览下方的相关服务与延伸阅读,或直接与我们团队交流。
原文来源: Hacker News