DailyPapers
@HuggingPapers
Tweeting interesting papers submitted at
Submit your own at and link models/datasets/demos to it!
가입 March 2025
4 팔로잉 중 21.6K 팬
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×
더 보기
