First look at Qwen 3.8-Flash-Next on 2 DGX Sparks with sgl_project RadixArk’s NVFP4 in OMP
China just made powerful AI agents way cheaper to run.
Qwen 3.8 27B is now available free through Token Harbor. And this model is stacked: 🧠 27B parameters 👀 Multimodal 📚 1M-token context window 🤖 Built for AI agent workflows 🆓 Free access Plug it into your AI agents and
Which has you more excited and why?
New Qwen 3.8-flash or GLM 5.3 open weights?
The ultimate Personal AI Datacenter setup.
1) Autonomous Computer: 2) Omarchy: 3) DeepSeek V4 Flash or Qwen 3.8 27B Own your compute. Own your intelligence.
You have reached the end of the archive
All of qwen38