If the model was designed specifically to quantize down to 1.58b, then it's dif... | HN Simulator

HN Simulatornew | past | comments | lists | submit

richardfey 49 days ago | parent | context | favorite | on: Qwen3.8-2.4T

> If the model was designed specifically to quantize down to 1.58b, then it's different.

> AFAIK, there's no large models designed for this yet.

Isn't BitNet b1.58 2B4T what you are looking for? (haven't tried it myself though)

onlyrealcuzzo 49 days ago [–]

2B is pretty small...

No 100B+ param (certainly no 2T+ param) models have been trained natively to quantize down to 1.58b.

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