EnCharge AI launches its analog in-memory EN100 AI accelerator

EnCharge AI has unveiled its EN100 AI accelerator chip.

Designed to bring AI capabilities to laptops, workstations, and Edge devices, the AI chip startup claims it is the first AI accelerator built on precise and scalable analog in-memory computing.

The EN100 is available in two form factors, the M.2 for laptops and the PCIe for workstations. The former offering delivers more than 200 tops of AI compute power in an 8.25W power envelope, while the latter features four NPUs (Neural Processing Units) reaching approximately 1 petaops, delivering GPU-level compute capacity at a fraction of the cost and power consumption, EnCharge claims.

While the company did not name the other offerings, it says that when compared to competing solutions, “EN100 demonstrates up to ~20x better performance per watt across various AI workloads,” while also providing up to 128GB of high-density LPDDR memory and 272Gbps of bandwidth.

Analog in-memory compute is a novel chip architecture that combines analog computing techniques with in-memory computing architecture to improve compute efficiency and memory bottlenecks, two challenges associated with traditional approaches to AI compute.

The company has previously said that its chip architecture uses existing semiconductor manufacturing processes, allowing it to rapidly scale production.

“The fundamental shift in AI computing architecture, rooted in hardware and software innovations that have been de-risked through fundamental research spanning multiple generations of silicon development,” said Naveen Verma, CEO at EnCharge AI. “These innovations are now being made available as products for the industry to use, as scalable, programmable AI inference solutions that break through the energy-efficient limits of today’s digital solutions. This means advanced, secure, and personalized AI can run locally, without relying on cloud infrastructure. We hope this will radically expand what you can do with AI.”

Founded in 2022 after it spun out of Princeton University, EnCharge AI has been developing analog in-memory chip technology, which it claims is able to achieve orders-of-magnitude higher compute efficiency and density compared to today’s best-in-class solutions.

In February 2025, the company announced it had closed an oversubscribed $100m Series B funding round, bringing the total amount raised by EnCharge AI to more than $144m.

Source: https://www.datacenterdynamics.com/