Raises Additional $70M to Bring its Multimodal Generative AI Chips to Edge Devices Raises Additional $70M to Bring its Multimodal Generative AI Chips to Edge Devices, a Silicon Valley–based startup producing embedded machine learning (ML) system-on-chip (SoC) platforms, has announced a $70 million extension funding round as it prepares to bring its second-generation chipset to market. The oversubscribed round, led by Maverick Capital, brings's total funding to $270 million.

The new chip is specifically built to handle the growing demand for multimodal generative AI processing at the edge, enabling devices like robots, drones, diagnostic machines, and autonomous vehicles to handle more collaborative human-machine interactions.

The rapid rise of generative AI is fundamentally changing the way humans and machines work together, with multimodal inputs like text-to-speech, text-to-image, speech-to-text, and image-to-video becoming increasingly common.'s MLSoC is designed to power and process any modality customers prefer, with improved performance and power efficiency compared to its first-generation chip.

"AI — particularly the rapid rise of generative AI — is fundamentally reshaping the way that humans and machines work together," said Krishna Rangasayee, Founder and CEO at "Our customers are poised to benefit from giving sight, sound and speech to their edge devices, which is exactly what our next generation MLSoC is designed to do."'s proprietary combination of silicon and software allows the MLSoC to adapt to any framework, network, model, sensor, or modality, making it a versatile platform for edge AI applications. The company's Palette software features, such as static scheduling and double buffering, enable proactive data prefetch, allowing customers to process any model size or type on the silicon architecture.

The second-generation MLSoC incorporates innovations from industry partners, including an Arm Cortex-A CPU for overall application development, Synopsys EV74 Embedded Vision Processors for pre-and-post processing in computer vision applications, and TSMC's N6 technology for further performance and power optimizations.

" possesses the essential trifecta of a best-in-class team, cutting-edge technology and forward momentum, positioning it as a key partner for customers traversing this tectonic shift," said Andrew Homan, Senior Managing Director at Maverick Capital. "We are excited to join forces with to seize this once-in-a-generation opportunity."

As edge AI continues to scale,'s one software-centric platform for all edge AI is poised to help customers navigate growing software complexity and increasing demand for AI performance. The company's recent results in the MLCommons MLPerf Inference benchmark further validates its market leadership in performance and power efficiency for embedded edge applications. achieved best-in-class results in the MLPerf benchmark for Edge category for the third consecutive time. In the MLPerf 4.0 submission, maintained dominance in FPS/W, improving performance across all evaluated workloads with increases in FPS ranging between 7% and 16% in the Closed Edge Power category over its 3.1 submission last August.

With the additional funding, is well-positioned to continue meeting customer demand for edge AI/ML with its first-generation MLSoC while accelerating the development of its second-generation chip.

Let’s stay in touch. Get the latest AI news from Maginative in your inbox.