I asked it to implement the simplest todo in ghostty codebase and it failed badly - kept going in circles fixing one compile error and introducing another. Qwen 3.8 was slower (40 tok/s compared to 75) but did get it done.

> Qwen 3.8 was slower

Is that Qwen 3.8 27B? Because yes, you'd expect a plain 27B model to be better than a 24B-A2B MoE model all else being equal.

(All else isn't equal though of course - Qwen models are very, very good at coding)

Gemma-4 26BA4B would be a more similar comparison.

That's not surprising. Even Liquid's own documentation states that coding isn't this model's strong suit. Its strength lies in tool calling.

Have you tried Gemma-4 26BA4B? I feel like it is underrated for tasks like that, but maybe I've just been lucky with my use cases.

in my experience it's stronger for terminal use, like chaining bash calls, monitoring background tasks, etc. rather than for straight up coding/swe work. Good with web search and file search rather than just editing software.