招股书显示，摩尔线程主要从事GPU及相关产品的研发、设计和销售。自2020年成立以来，公司以自主研发的全功能GPU为核心，致力于为AI、数字孪 生、科学计算等高性能计算领域提供计算加速平台。公司已成功推出四代GPU架构，并拓展出覆盖AI智算、云计算和个人智算等应用领域的计算加速产品 矩阵。 摩尔线程在国内GPU领域具有一定的技术优势，基于自主研发的MUSA架构，公司率先实现了在单芯片架构上同时支持AI计算加速、图形渲染、物理仿真以 及超高清视频处理所需计算能力的突破。相比采用GPGPU、ASIC等技术路线的其他单一AI加速卡产品，MUSA架构技术具备更强的计算通用性、更优的技 术演进能力、更佳的生态兼容性以及更广泛的市场适应性。 摩尔线程主要对外销售板卡产品的型号为S4000、S3000、S50。其中，S3000板卡产品2023年开始出货，2024年销量同比增长接近200%;对外销售一体机产品 的型号为S4000、S3000、S2000;主要销售的集群产品为S3000集群、S4000集群、S5000集群，合计销售10套集群。 财务方面，于2023年度、2024年度及2025年1-6月，摩尔线程实现营业收入约为 ...

Core Viewpoint - Moore Threads has successfully passed the IPO review for the Science and Technology Innovation Board, aiming to raise 8 billion RMB for the development of next-generation AI and graphics chips, as well as to supplement working capital [1] Company Overview - Moore Threads, established in 2020, focuses on the research, design, and sales of GPUs and related products, providing computing acceleration platforms for high-performance computing fields such as AI and digital twins [1] - The company has launched four generations of GPU architectures and has developed a product matrix covering AI intelligent computing, cloud computing, and personal intelligent computing applications [1] Technological Advantages - The company has achieved significant breakthroughs in the domestic GPU field with its self-developed MUSA architecture, which supports AI computing acceleration, graphics rendering, physical simulation, and ultra-high-definition video processing on a single chip [2] - Moore Threads' products, including the S3000 and S4000 models, have shown performance metrics approaching international advanced levels, with the MTT S80 graphics card's single-precision floating-point performance nearing that of NVIDIA's RTX 3060 [2] Financial Performance - For the fiscal years 2023, 2024, and the first half of 2025, Moore Threads reported revenues of approximately 124 million RMB, 438 million RMB, and 702 million RMB, respectively, with net losses of 1.673 billion RMB, 1.492 billion RMB, and 271 million RMB [3][4] - The company anticipates achieving consolidated profitability by 2027, with projected gross margins of 77% for AI intelligent computing and professional graphics acceleration businesses by 2025 [5] Fundraising and Investment Projects - The IPO proceeds will be allocated to the development of next-generation AI training and inference chips, graphics chips, AI SoC chips, and to supplement working capital, totaling 800 million RMB [6][8]