Ornith 1.5 35B is VERY Good - Full Test & Quant Comparison!
Source
Bijan Bowen
Author
Bijan Bowen
Date
Terms in this piece · Glossary
quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
Why it matters
Shows where Q4 degrades against Q8 on browser, FPS, C++, CAD and frontend builds — the practical trade-off when fitting a 35B model onto local hardware.
