One prompt, no cloud: Qwen 3.8 27B running locally on a Mac Studio M3 Ultra (256 GB RAM) built this…
One prompt, no cloud: Qwen 3.8 27B running locally on a Mac Studio M3 Ultra (256 GB RAM) built this autonomous 3D water sim — a caldera where rain and springs feed one lake. Three.js, no physics engine, no assets. 19/19 tests, nothing needed fixing.
I tried three models with the same thing, and each one gave results again 🤔
The GLM had the best colors, the Qwen surprised me the most, and the Gemini finished under 2 minutes and 15 seconds. After trying all three, my final choice: Qwen 3.8 Max and GLM 5.3.
Local AI is moving too fast now, there is something new every day.
Qwen 3.8 27B running on consumer laptops and beating cloud models people pay for. A new engine called FreeToken putting a 35B model on an 8GB laptop. 128GB local AI boxes from AMD and NVIDIA becoming normal desk
AI is getting more capable, but it’s also getting smaller, more local, and more collaborative.
🧠🤖 We tested Qwen 3.8, local models, multi-agent workspaces, new coding tools, and more to see where AI workflows are actually heading. The bigger question we kept coming back to:
You have reached the end of the archive
All of qwen38