hermes-ai.netis an unofficial, independent community guide to Hermes Agent, with localized docs, release notes, desktop notes, and practical setup paths.
DASLab Squeezes a 176.9B Coding Model Down to 32GB Hardware
ISTA's DASLab shrinks a 176.9B-parameter Qwen mixture-of-experts model to 29.6GB resident memory by pruning half its experts and quantizing the rest to 3.5 bits.
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read
ISTA's DASLab shrinks a 176.9B-parameter Qwen mixture-of-experts model to 29.6GB resident memory by pruning half its experts and quantizing the rest to 3.5 bits.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
