A model that beats GPT on some benchmarks is running on my desk right now.
Nobody is covering it. If you have two Sparks and you are not checking out Qwen3.8-Flash, you are missing out. Tools at 128k context, the lane where most local models die: 89.7 tok/s, zero XML leakage.
Yooooo qwen 3.8 max wtffffff!!!!
I asked it for a simple thing i was just testing it out for some name ideas, next thing i look up and its in a loop talking about crazy ah stuff like "I am unraveling the fabric of reality, tracing the collapse from the intimate bonds of
Tellusim chat tool now support Engine SDK.
Qwen 3.8 Flash Next created this 3D dungeon maze from a single prompt: "Make a 3D dungeon maze with a 1st-person view camera, using the Tellusim Engine SDK with RenderSystem and Primitives plugins". It generated the complete C++ code
A GPU that almost everyone has, did this without a single line of handwritten code.
An RTX 3060, the most common GPU on Steam, built an entire game. → Bonsai2, a Qwen 3.8 27B model, running on 12GB of VRAM. → 5 hours, 328 thousand tokens, 2,368 lines. The GPU
You have reached the end of the archive
All of qwen38