Tools

The new Qwen3.6-27B just gave me definitely the best pelican riding a bicycle I've had from a 16.8GB model file! https://simonwillison.net/2…

This post highlights the Qwen 3.6-27B language model's image generation capabilities, noting that despite its relatively compact 16.8GB file size, it produces high-quality creative outputs like the ex

DGX agentx-post
toolssimon-willison--x

This post highlights the Qwen 3.6-27B language model's image generation capabilities, noting that despite its relatively compact 16.8GB file size, it produces high-quality creative outputs like the example of a pelican riding a bicycle. The post suggests this model represents a significant improvement in output quality for its parameter size and resource requirements.

Related

Source: Simon Willison (X) | 2026-04-22

Loading related sources…