logoalt Hacker News

asaddhamani • today at 7:46 PM • 1 reply • view on HN

QAT models are trained to quantize well? I don’t get the concern here.


Replies

woadwarrior01 • today at 7:58 PM

Please read their blog post. This isn't a run of the mill QAT post trained model (like Gemma 4 QAT). It was natively trained in NVFP4, through and through.

> Most of Inkling 2 Mini’s weights were trained and are deployed natively in NVFP4, with the last four layers in MXFP8.

https://thinkingmachines.ai/news/inkling-2-mini/