SambaNova Systems Unveils Fastest Chip for Agentic AI, Secures $350 Mn, Partners with Intel

SambaNova Systems has launched its SN50 AI chip, which the company says delivers performance up to five times faster than competitive chips while cutting inference costs by up to threefold, as it targets large-scale agentic AI workloads and autonomous AI agents.

The new SN50 processor, built on SambaNova’s proprietary Reconfigurable Data Unit (RDU) architecture, supports unprecedented throughput and scale for real-time AI inference, linking up to 256 accelerators with multi-terabyte-per-second bandwidth. SambaNova claims this enables enterprises to run larger models with higher responsiveness and lower operational costs.

To accelerate deployment and scale the product globally, SambaNova announced a multi-year strategic collaboration with Intel and raised over $350 million in Series E funding from new and existing investors including Vista Equity Partners, Cambium Capital, Battery Ventures and Intel Capital. The funding will expand manufacturing, cloud capacity and go-to-market efforts.

“AI is no longer a contest to build the biggest model,” said SambaNova co-founder and CEO Rodrigo Liang. “With the SN50 and our deep collaboration with Intel, the real race is about who can light up entire data centers with AI agents that answer instantly, never stall, and do it at a cost that turns AI from an experiment into the most profitable engine in the cloud.”

“By combining Intel’s leadership in compute, networking, and memory with SambaNova’s full-stack AI systems and inference cloud platform, we are delivering a compelling option for organisations looking for GPU alternatives to deploy advanced AI at scale,” Kevork Kechichian, EVP and General Manager of Intel’s Data Center Group, added.

SoftBank Corp. will be the first customer to deploy SN50 within next-generation AI data centers in Japan, underscoring demand for high-performance agentic AI infrastructure