AgenticLinux (Fedora 45 based) now works on DGX Spark 🚀
128 GB of unified memory, a local Qwen 3.8 27B, and OpenClaw doing real work on an immutable box via llmman: steipete jonmasters nullr0ute might be interested in this one.
Reminder that local ai is also important.
This is Qwen 3.8 flash-next. The entire generation ran locally on my 5090 from the video to the actual code. I can’t wait for Qwen 4 series.
If you’re stuck on one llm engine assuming it’s the best, check again
Tested qwen 3.8 27b on 3090 (350w, 64k ctx) with 4 serving engines hyperqwen: fastest at everything except loading. 180 tok/s avg, and 448 tok/s total at 8 users tensorfold: same exl3 files as exllamav3 but
Like GPT-6 Astra, Qwen 3.8 27B can interpret model weights
Treat the mechanism as a merge gate: prove it in CI before the next demo reel.
You have reached the end of the archive
All of qwen38