DailyPapers
@HuggingPapers
Tweeting interesting papers submitted at
Submit your own at and link models/datasets/demos to it!
参加 March 2025
4 フォロー中 21.6K ファン
Why the recurrent half of a hybrid LLM is actually easy to quantize
Minima quantized all 496 linear layers of Qwen3.8-27B — including Gated DeltaNet — to NVFP4 W4A4, matching BF16 performance while cutting size ~2.9×
もっと見る
