Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s
Trending on Hacker News: Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s (505 points / 252 comments, via github.com)
In one line
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
Opening excerpt
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 …
(Excerpted from the original; full article via the source link below.)
This story hit the Hacker News front page today (505 points / 252 comments, via github.com). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.
Source: Hacker News