Emad@EMostaque腾讯混元发布旗舰级295B参数模型Hy3的1-bit与4-bit量化版本，可在单GPU上运行。Emad Mostaque引用该消息并指出，Hy3在1-bit量化下SWE-bench Verified得分75.4%、SWE-bench Pro得分53.9%，性能惊人。模型仅88GB，可在Macbook Max上运行。他预期基于NVP4训练的模型性能下降更少，并建议未来可全面采用二进制推理。用户可通过llama.cpp运行Hy3并启用MTP。
75.4% SWE Bench Verified / 53.9% SWE Bench Pro on 1 bit quantisation is 🤪
This is in line with my expectations &； you can expect even lower drop off with NVP4 base trained models - why not run everything binary？
88 Gb so works on a Macbook Max
Emad@EMostaque · X腾讯混元发布旗舰级295B参数模型Hy3的1-bit与4-bit量化版本，可在单GPU上运行。Emad Mostaque引用该消息并指出，Hy3在1-bit量化下SWE-bench Verified得分75.4%、SWE-bench Pro得分53.9%，性能惊人。模型仅88GB，可在Macbook Max上运行。他预期基于NVP4训练的模型性能下降更少，并建议未来可全面采用二进制推理。用户可通过llama.cpp运行Hy3并启用MTP。
75.4% SWE Bench Verified / 53.9% SWE Bench Pro on 1 bit quantisation is 🤪
This is in line with my expectations &； you can expect even lower drop off with NVP4 base trained models - why not run everything binary？
88 Gb so works on a Macbook Max