Fun Spaceship Scene (no audio) - I prompted a tiny LLM local PC model Qwen 3.8-27b to create this on a modest 6GB RTX 3050.
Open source LLMs are on fire right now.
GLM 5.3 especially: three times fewer parameters than Kimi K3, and it still comes out ahead. Could not resist seeing what that does in 3D. Ran it through Blender, Unity and Godot, and took Qwen 3.8 Max along because that one is a curious
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
You have reached the end of the archive
All of qwen38