Nanyang Singtech Debuts SingNova-H Studio: First RISC-V Dataflow Architecture AI PC with 200 TOPS for Local Large Models

SINGAPORE, May 21, 2026 (GLOBE NEWSWIRE) -- At this year’s ATxSG technology exhibition, Nanyang Singtech, a deep-tech company incubated by Nanyang Technological University (NTU), unveiled the SingNova-H Studio for the first time. This next-generation AI PC is powered by a RISC-V dataflow architecture system-on-chip (SoC). The debut marks a critical step for the company into full-scenario intelligent infrastructure, spanning intelligent computing, smart finance, intelligent energy, and embodied intelligence.

The SingNova-H Studio arrives at a pivotal moment for the AI industry. As enterprises and developers increasingly face cloud dependency, data privacy risks, and soaring inference costs, the market demand for powerful local AI computing has never been more urgent. Nanyang Singtech’s solution is a compact desktop workstation that delivers 128 GB of unified high-capacity memory and 200 TOPS of local large-model computing power—without ever sending data off-premises.

Breaking the Control-Flow Bottleneck

Traditional control-flow architectures have long suffered from the "memory wall"—the efficiency drain caused by repeatedly shuttling data between memory, cache, and processing units. The SingNova-H Studio fundamentally overcomes this limitation through a RISC-V dataflow architecture with control-data collaborative optimization. This design ensures high-concurrency, low-latency execution of video processing, AI inference, and scientific computing workloads on a unified platform.

At its core is a 12-core RISC-V CPU running at 2.0 GHz, integrated with an AI accelerator delivering 200 TOPS (INT8) and 32 TFLOPS (FP16). This throughput enables the workstation to run large language models with up to 70 billion parameters entirely on the device. All data remains local, delivering ultimate privacy and security while eliminating the network latency common in cloud-based inference.

Memory and Bandwidth for Real-World Workloads

Edge AI workloads are notoriously memory-hungry. The SingNova-H Studio features up to 128 GB of LPDDR5 ECC unified memory, providing ample room for massive model weights and high-resolution datasets. Storage comes via flexible NVMe PCIe 4.0 SSD configurations, while dual 10 GbE Ethernet ports deliver high-throughput connectivity for clustered deployments or data-intensive pipelines. The system also includes a PCIe 4.0 x16 expansion slot for discrete GPUs or additional accelerators, plus optional Wi-Fi 6E and Bluetooth 5.3 modules.

Display outputs are equally robust: one HDMI 2.1 (4K@60 Hz), one DP 1.4a, and one USB-C (2K@60 Hz) support multi-monitor development environments. Despite this capability, the unit maintains a compact, minimalist industrial design with an efficient thermal structure, keeping typical power draw between 10 W and 75 W—balancing desktop elegance with engineering practicality.

A Complete Software Ecosystem

Hardware innovation alone is not enough; accessible software is equally critical. Nanyang Singtech plans to equip the SingNova-H Studio with a mature, full-stack software ecosystem based on Linux and other open-source operating systems. The platform includes a professional programming toolchain and compatibility with mainstream AI frameworks, lowering the barrier for developers, researchers, and creatives building on open hardware.

Cross-Industry Application Scenarios

The SingNova-H Studio spans multiple verticals. In enterprise settings, it serves as a private AI inference engine for secure deployment of generative models in document analysis, code generation, and knowledge management. For security and smart-city operators, the system supports parallel camera access, delivering real-time video analytics—facial recognition, behavioral analysis, and video structuring—at 128-channel 1080p@30 fps decode or 64-channel encode.

In industrial and IoT environments, it acts as a high-reliability edge-computing node for smart factories, robotics, and autonomous driving, providing the deterministic low latency required for real-time decision-making and closed-loop control. Creative professionals benefit from accelerated Stable Diffusion text-to-image generation, video editing, and 3D creation, while universities and research institutes leverage the open-source RISC-V architecture for ecosystem development, algorithmic research, and experimental teaching.

A Milestone for Singapore’s Deep-Tech Ecosystem

Nanyang Singtech’s debut at ATxSG highlights Singapore’s emergence as an innovation hub for advanced computing hardware. By combining NTU’s research heritage with commercial engineering execution, the company is positioning itself as a key infrastructure provider in the global shift toward localized, efficient, privacy-preserving AI.
"SingNova-H Studio embodies our belief that the future of intelligent computing must be open, local, and scalable," the company stated at the event. "We are not merely building a faster PC; we are redefining what an edge intelligent workstation can deliver for developers and enterprises worldwide."

About Nanyang Singtech

Nanyang Singtech is a Singapore-based deep technology company incubated by Nanyang Technological University. The company focuses on intelligent computing, smart finance, intelligent energy, and embodied intelligence, delivering full-scenario intelligent infrastructure covering intelligent computing, storage, energy, and autonomous driving systems.

Media Contact
Company：NANYANG SINGTECH PTE. LTD.
Contact Person: LONG HAIYAN
Email: LONGHAIYAN@nanyang-singtech.com
Website: https://www.nanyang-singtech.com/

Disclaimer:  This content is provided by NANYANG SINGTECH PTE. LTD. The statements, views, and opinions expressed in this content are solely those of the content provider and do not necessarily reflect the views of this media platform or its publisher. We do not endorse, verify, or guarantee the accuracy, completeness, or reliability of any information presented. This content is for informational purposes only and should not be considered financial, investment, or business advice. All investments carry inherent risks, including the potential loss of capital. Readers are strongly encouraged to conduct their own due diligence and consult with a qualified financial advisor before making any investment decisions. Neither the media platform nor the publisher shall be held responsible for any inaccuracies, misrepresentations, or financial losses resulting from the use or reliance on the information in this press release. Speculate only with funds you can afford to lose. In the event of any legal claims or concerns regarding this article, we accept no liability or responsibility. Globenewswire does not endorse any content on this page.

Legal Disclaimer: This media platform provides the content of this article on an "as-is" basis, without warranties or representations of any kind, express or implied. We assume no responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained herein. Any complaints, copyright issues, or inquiries regarding this article should be directed to the content provider listed above.

A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/3a8e1dac-fd0a-4e65-9665-fe20cb08bc4b

Legal Disclaimer:

EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.