VSORA Launches Europe’s Most Powerful AI Inference Chip
- Production of ultra-high-performance AI chip called Jotunn8 begins
- Redefining cost-effective, high-performance AI inference deployment at scale
- Semiconductor Manufacturing Partnership for quality, scalability, access to cutting-edge fabrication technologies
PARIS –– October 22, 2025 –– VSORA, a French semiconductor innovator, today announced the production launch of Jotunn8, an artificial intelligence (AI) inference chip engineered to power next-generation data center applications delivering breakthrough efficiency and scalability for large-scale artificial intelligence deployment.
With Jotunn8 now in production, VSORA stands as the only European company delivering AI inference chips that compete directly with those of leading U.S. technology giants. While matching the raw compute power of today’s most advanced solutions, Jotunn8 achieves more than 3X higher real-world performance and operates at less than half the power, providing a decisive advantage in efficiency, energy savings and sustainability for modern data centers.
“Jotunn8 allows us to compete on the global stage with a homegrown, energy-efficient AI chip,” remarks Khaled Maalej, VSORA’s founder and CEO. “It’s about performance and a pivotal moment not just for VSORA, but for European technology. Europe now has a seat at the table to guide the future of AI.”
Redefining AI Inference Deployment
As demand for AI accelerates, so does the need for chips that can run AI models efficiently, securely and affordably. AI inference—the process of running trained models to generate responses, predictions or decisions—is becoming the backbone of all consumer devices from virtual assistants to self-driving cars.
VSORA’s Jotunn8 (J8) chip is redefining cost-effective, high-performance AI inference deployment at scale with a purpose-built architecture that overcomes inherent GPU limitations. While most chips are optimized for AI training, Jotunn8 is purpose-built for AI inference, enabling fast decision-making with minimal power draw.
Jotunn8 delivers 3,200 teraflops of compute power at more than 50% utilization and 50% less power consumption, shattering the performance barriers of conventional GPUs and achieving real-world performance that surpasses today’s top-tier chips. Scalable by design, J8 integrates easily into modern data centers and AI infrastructure, setting a new standard for efficient, high-performance inference computing.
VSORA is partnering with leading global semiconductor manufacturers to bring the chip to production, ensuring quality, scalability and access to cutting-edge fabrication technologies. It is also working with strategic stakeholders to prepare for large-scale deployment and industrial adoption.
Full volume production is expected in Q1 2026. Pricing will be available upon request.
About VSORA
Founded in Paris in 2015, VSORA is a European leader in high-performance AI silicon solutions. Its chips can be utilized in a wide range of next-generation technologies, from AI-powered data centers to autonomous systems and industrial robotics. VSORA is headquartered in France, with offices in Japan, Korea, Singapore, and Taiwan.
Related Semiconductor IP
- LPDDR6/5X/5 PHY V2 - Intel 18A-P
- ML-KEM Key Encapsulation & ML-DSA Digital Signature Engine
- MIPI SoundWire I3S Peripheral IP
- ML-DSA Digital Signature Engine
- P1619 / 802.1ae (MACSec) GCM/XTS/CBC-AES Core
Related News
- VSORA Raises $46 Million to Bring World’s Most Powerful AI Inference Chip to Market
- Fractile Licenses Andes Technology's RISC-V Vector Processor as It Builds Radical New Chip to Accelerate AI Inference
- DEEPX Signs 2nm Process Agreement with Samsung Foundry to Develop World’s First On-Device Generative AI Chip ‘DX-M2’
- ChipAgents Raises Oversubscribed $21M Series A to Redefine AI for Chip Design
Latest News
- proteanTecs Appoints Noritaka Kojima as GM & Country Manager and Opens New Japan Office
- QuickLogic Reports Fiscal Third Quarter 2025 Financial Results
- lowRISC® and Partners to Deliver Commercial-Quality, Open-Source CHERI Secure Enclave with InnovateUK Support
- M31 Technology: Advanced Nodes and Royalties Drive 20% Revenue Growth Target for 2025
- Tachyum Unveils 2nm Prodigy with 21x Higher AI Rack Performance than the Nvidia Rubin Ultra