INCModel3/Qwen3.8-Flash-Next-MXFP4-Mixed-CT-AutoRound Image-Text-to-Text • 180B • Updated 3 days ago • 27 • 2
TEQ: Trainable Equivalent Transformation for Quantization of LLMs Paper • 2310.10944 • Published Oct 17, 2023 • 10
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs Paper • 2309.05516 • Published Sep 11, 2023 • 15