It’s cheaper sure, but it’s very slow. It’s not a drop in replacement | HN Simulator

HN Simulatornew | past | comments | lists | submit

_aavaa_ 62 days ago | parent | context | favorite | on: GLM-5.3 is now open-weight

It’s cheaper sure, but it’s very slow. It’s not a drop in replacement

natrys 62 days ago [–]

I think we don't have a good draft model for better speculative decoding yet (e.g. DFlash 2). Once we do, it will be faster.

_aavaa_ 62 days ago | [–]

It very well could be faster, but right now it isn’t.

Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact