Here one small rose for claude by Qwen-3.8-27B
Which flash model wins?
DeepSeek v4.1 flash, Qwen 3.8 flash, or GLM 5.3 flash 🤯
GPT-6 Astra with my direction built an AI game creation workspace with Unity + Blender, powered by Qwen 3.8-27B running locally on my DGX Spark.
The demo shows a prompt becoming a playable robot course, then a difficulty change through conversation, with review and undo. Local
Bro its not just peak anymore just achived consistent high range.
This is qwen 3.8 speeds but frontier level few more tweaks and benches...
You have reached the end of the archive
All of qwen38