Qwen 3.8 max is Extremely terrible(non thinking mode)
Made a short video on the ultimate solo dev vibe coding setup ⚡️
OMP + Qwen 3.8 for building apps DeepSeek Flash V4 for vision One developer + an AI coding stack = seriously powerful. The solo dev era is getting wild.
I'll pull the original post first so the rewrite can match its length
Structure, and meaning.The post quotes an article and includes a video, so I’m checking both before rewriting.ABSURD. Qwen 3.8 27B is running locally on an RTX 4060 with just 8GB of VRAM. That's a 64k
Qwen 3.8 27b on the agent mode harness.
Built itself a python app to generate the single html. Prompt in the first comment proves the harness value 🏆👇⬇️ ..also impressive workspace structure in agent mode 👏
You have reached the end of the archive
All of qwen38