mit-han-lab/llm-awq GitHub README

Fields

id

sources/qlab2-awq-readme

URL

https://github.com/mit-han-lab/llm-awq

Publisher

MIT HAN Lab

Kind

repo

Accessed

2026-10-03

notes

AWQ canonical group size is 128 (q_group_size 128 in every example; the model zoo is indexed as INT4-g128 / INT3-g128). TinyChat with LLaMA-3-8B on RTX 4090 is claimed 2.7x faster than FP16 for W4A16 (vendor claim). | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.

Notes

AWQ canonical group size is 128 (q_group_size 128 in every example; the model zoo is indexed as INT4-g128 / INT3-g128). TinyChat with LLaMA-3-8B on RTX 4090 is claimed 2.7x faster than FP16 for W4A16 (vendor claim). | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.

Cross-references

This record references no other records.