ResearchBenchmarksModel Compression on Nemotron-8BFollow2.9Model Size (GB)UniQL2.3685.9599.5513.141Dec 3, 2025Evaluation ResultsMethodMethodLinksModel Size (GB)UniQLW-bit=4, Prun. p%=35%W-bit=4, Prun. p%=35%2025.122.9UniQLW-bit=4, Prun. p%=0%W-bit=4, Prun. p%=0%2025.124.1FP16W-bit=16, Prun. p%=0%W-bit=16, Prun. p%=0%2025.1216.2