SpacemiT, a Chinese company focused on RISC-V chips, released its new K3 AI chip on January 29, 2026. The chip combines general computing with AI processing, providing a flexible, energy-efficient solution for smart devices as well as edge computing.
The K3 chip showcases eight CPU cores, running at up to 2.4GHz, as well as can manages up to 60 TOPS (trillion operations per second) for AI tasks. It supports up to 32GB of memory and is made for medium-scale AI models, with low power consumption between 15 to 25 watts.
SpacemiT's K3 is one of the first RISC-V AI chips made for local AI processing, supporting mainstream AI frameworks like Triton and TileLang. It aims to make AI more accessible for developers by offering an open-source, customizable platform.
The company also provides supporting products, including single-board computers as well as robot core boards, and plans to expand its RISC-V chip ecosystem to support a range of AI applications.
As per Coherent Market Insights, the Artificial Intelligence in Hardware Market will grow at a 16.2% compound annual growth rate (CAGR) from 2025 to 2032, from USD 65.32 Bn in 2025 to around USD 186.97 Bn by 2032. There is rapid adoption of AI technologies across industries for applications such as robotics, smart homes, and autonomous vehicles can boost demand for specialized AI hardware such as GPUs, chips, and other acceleration hardware during the forecast period. The market growth is driven by increasing investments by major technology players such as Intel, IBM, and Google in AI hardware startups.
“We believe the long-term direction of edge computing architectures is a transition from closed to open systems,” said Chen Zhijian, founder and CEO of SpacemiT, at the launch event. “x86 is highly closed, Arm is semi-open, while RISC-V is fully open. In the long run, open instruction sets are more likely to become the foundation of global computing.”
Chen added that RISC-V carries particular significance for China’s semiconductor industry. “In the past, Chinese computing chips were largely limited to domestic markets. Open architectures create a new path for Chinese chips to integrate more naturally into the global technology ecosystem.”
“In the AI era, CPUs can no longer be just control processors,” he said. “They must also provide native AI computing capabilities. This is similar to the shift from feature phones to smartphones — a fundamental change in the form of computing.”
Source:
News: SpacemiT
