Mythic has raised $125 million in an oversubscribed funding round led by DCVC, marking a dramatic turnaround for the company. The capital injection aims to address one of AI’s biggest challenges its enormous energy consumption both in data centers and at the edge. Mythic’s novel architecture delivers performance that is 100 times more energy-efficient than current leading GPUs and competing AI ASICs.
“Mythic will win based on this fundamental insight: energy efficiency will define the future of AI computing everywhere,” said CEO Taner Ozcelik.
The company’s unique semiconductor architecture closely mirrors the energy efficiency of the human brain and can serve multiple sectors across the AI market. Mythic’s analog AI chiplets support AI models in robotics, automotive, and defense industries, as well as 1T+ parameter Large Language Models (LLMs) in data centers. Beyond substantial energy savings, these chiplets reduce latency, lower costs, and increase throughput. With the world’s first production-ready analog computing silicon validated by the Department of Defense, leading automotive OEMs, and defense partners, Mythic positions the United States with a strategic edge in global AI leadership shifting the competition from energy-intensive production to smarter, more sustainable AI solutions.
AI Authority Trend: LCPC AI Democratizes AI Computing for Everyone Worldwide
The funding comes after Mythic underwent extensive reinvention under new leadership, rebuilding its architecture, roadmap, software, and overall strategy. This transformation attracted a consortium of investors, including NEA, Atreides, Future Ventures, Softbank KR, S3 Ventures, Linse Capital, Honda Motors, and Lockheed Martin. These partnerships accelerate Mythic’s expansion into the trillion-dollar automotive and defense markets.
Massive energy consumption challenges GPUs, as modern AI workloads could consume up to one-tenth of the U.S. power grid by decade’s end. GPUs, based on the 1945-era Von Neumann architecture, waste significant energy transferring data between memory and processors. Mythic’s APUs unify memory and computation, mirroring the human brain, and perform matrix multiplications in analog, achieving 120 trillion operations per second per watt 100x the efficiency of top GPUs.
“Mythic will win based on this fundamental insight: energy efficiency will define the future of AI computing everywhere. Much as GPUs have become the accelerated computer of choice next to CPUs due to their performance per watt benefits, our insanely energy-efficient APUs will become the accelerated computer of choice next to GPUs,” said Dr. Ozcelik.
AI Authority Trend: GIGABYTE Unveils “Beyond Edge” Vision to Redefine AI Computing
NEA Partner Aaron Jacobson added, “Their APU platform is a clean-sheet reinvention of the AI infrastructure one that collapses today’s limits on energy and cost. This significant new funding gives Taner and Mythic the runway to execute quickly and at scale and leave outdated chip architectures behind.”
Mythic’s APUs also enable new sensing devices, such as Starlight, which operate under 1W and deliver 50x better image sensor performance using analog AI. Additionally, its CAMP SDK supports seamless deployment of Deep Neural Networks across ONNX, PyTorch, TensorFlow, and NVIDIA platforms.
Matt Ocko, Co-Founder and Managing Partner of DCVC, concluded, “Mythic is now fully empowered to scale the world’s next great computing architecture. Taner and his team have made a civilizational advance.”
With this latest funding, Mythic is poised to redefine energy-efficient AI across data centers, robotics, automotive, and defense, driving both cost savings and scalable AI performance.
AI Authority Trend: Celestial AI Closes Series C1 to Advance Next-Gen AI Computing
To share your insights, please write to us at info@intentamplify.com
