turboderp (@turboderp_) 's Twitter Profile
turboderp

@turboderp_

ID: 1673423377426444318

calendar_today26-06-2023 20:10:18

70 Tweet

712 Followers

33 Following

turboderp (@turboderp_) 's Twitter Profile Photo
turboderp
@turboderp_

5 months ago

Seems to still be true that larger models are less sensitive to quantization. Here is Mistral-Large 123B at 1.4 bits per weight, running on one 24 GB GPU. #AI or something