Meta debuts "quantized" versions of Llama 3.2 1B and 3B models, designed to run on low-powered devices and developed in collaboration with Qualcomm and MediaTek (Mike Wheatley/SiliconANGLE)

https://ift.tt/LesMlSf

Mike Wheatley / SiliconANGLE:
Meta debuts “quantized” versions of Llama 3.2 1B and 3B models, designed to run on low-powered devices and developed in collaboration with Qualcomm and MediaTek  —  Meta Platforms Inc. is striving to make its popular open-source large language models more accessible with the release of …

from Techmeme https://ift.tt/jfdXNOh