Chinese AI Company Breaks Bottleneck to Run 60 Billion Parameter Model on Mobile
爱范儿2653 字 (约 11 分钟)
92
A Chinese AI company has broken the bottleneck of running a 60 billion parameter model on mobile devices using ternary quantization, saving 6x memory with minimal performance loss.
入选理由：三值量化可节省6倍显存，保留97%模型能力，支持在8GB内存手机运行600亿参数模型。
FeaturedArticle#AI Model#Ternary Quantization#Ascend Chip#Edge AI#Model Compression中文