Bijan Bowen tests Ornith 1.0 in two local model sizes, including a 35B mixture-of-experts version with a smaller active parameter count. He compares practical memory requirements and generation behavior before moving to matched coding tasks.
The tests cover repository understanding, browser interfaces, game creation and Blender work. Both models show useful instruction following, while the larger model generally produces more coherent structure, stronger detail and fewer implementation failures.
Bowen treats Ornith as evidence that local coding models are improving quickly, but not as a reason to ignore hardware limits or output review. Users gain privacy and control while still accepting slower runs and more variable execution than top hosted systems.
Watch on YouTube
