#model efficiency
2 articles
Latest
Tools
Gemma 4 31B Punches Above Its Weight Class
Google's compact model delivers coding and daily tasks performance that rivals much larger competitors.
about 1 month ago1 min read
Tools
Google's TurboQuant Slashes LLM Memory Usage by 6x
New compression algorithm maintains output quality while dramatically reducing computational demands.
about 2 months ago3 min read