Qwen 3.8-27B is astonishingly good.
It one shotted this webGL fluid sim. It thought for such a long time and even added suggestions accurately without breaking anything later. All this using Unsloth Desktop, no agentic stuff yet.
AI/ML API tested Qwen 3.8 27B (self-hosted) against Claude Opus 4.6 on the same task
Creating one self-contained three.js file rendering a sunken Atlantis, plus a scripted 20-second camera flythrough. Both models handled the full camera path, with Qwen 3.8 27B running
MTP nearly doubled Qwen 3.8 27B on my 4090.
It also filled the card to the last 112 MB. Qwen 3.8 dropped today with a draft layer baked into the weights. The idea is simple: a small attached head guesses the next couple of tokens, the main model checks all the guesses in one
Qwen 3.8:27b (via Ollama) It works fine, but not at a practical speed...lol
You have reached the end of the archive
All of qwen38