Hugging Face Blog·· 2026-08-25AI 评分42
Hugging Face 提出 Quantization-Aware Healing：4-bit 压缩模型在 9 项评测中 7 项超越全精度原版
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
AI 导读
Hugging Face 论文提出 Quantization-Aware Healing（QAH）：将 GPT-OSS 120B 结构压缩至 60B 参数并量化到 MXFP4 后。
来源：Hugging Face Blog · huggingface.co