I’ve spent a long time experimenting with my own quantization of Qwen 3.8 Flash and a custom harness.
The results are starting to feel really good. Here’s a little cozy pixel-art game about feeding fish in a pond, made from this prompt: “Make a small pixel-art game in Rust
Cloudfare worker AI gives 10,000 free neurons every single day😳🔥
Cloudflare Workers AI gives you 10,000 free neurons daily basically free compute to experiment with powerful models. → Qwen 3.8 (27B Vision, 262K context) → Serverless inference at the edge → No GPU setup →
I handed Qoder a real task and watched its AI agent turn a goal into a finished result.
I chose the workspace, model, and permissions, then watched Qoder plan, use tools, make changes, and verify the output, all from the new task screen. I could also adjust, pause, or take over
I just gave qoder_ai_ide a real task: build a functional AI project management dashboard from scratch.
I described the outcome, chose Qwen 3.8 Flash, set the permissions, and watched it plan, build, test, and fix the project. The final dashboard has working task creation,
You have reached the end of the archive
All of qwen38