Liquid AI, the MIT-born leader in efficient foundation models, today announced native support for AMD’s latest Ryzen™ and Ryzen AI™ processors within the Liquid Edge AI Platform (LEAP), unlocking new performance gains for developers building high-quality, on-device AI solutions.
With this update, developers gain immediate access to Liquid’s low-latency, memory-optimized models, now natively accelerated on AMD’s latest “Zen 5” with AMD Radeon™ integrated graphics. The result is a unified software and hardware path for deploying privacy-preserving, real-time AI applications directly on PCs, without reliance on cloud inference.
Performance Without Compromise
Early benchmarks of Liquid’s LFM models running through the LEAP SDK on AMD hardware demonstrate:
- High throughput efficiency (tok/sec) at low power draw using AMD’s integrated compute accelerators
- Zero dependency on cloud APIs—preserving data privacy and reducing latency
- Seamless deployment for both consumer and enterprise software
With native processor support, developers can deliver lightweight, high-performing AI experiences that scale from consumer laptops to enterprise endpoints without modification or added complexity.
Purpose-Built for the Edge
Liquid’s LFM architecture is engineered for efficient edge inference. The new AMD-optimized approach with LEAP further reduces integration time for developers, providing a direct route for model deployment.
“This integration is about collapsing complexity for developers,” said Mathias Lechner, CTO and Co-Founder of Liquid AI. “By tuning LEAP for AMD Ryzen processors, we’re enabling teams to ship AI products faster—with the speed, efficiency, and control that edge applications demand.”
“Developers want a friction-free path to deliver AI that’s fast, private and power-efficient,” said Mark Papermaster, chief technology officer and executive vice president at AMD. “Pairing AMD Ryzen™ and Ryzen AI™ processors with Liquid AI’s memory-lean LFM models in the LEAP SDK collapses complexity, giving creators sub-100-millisecond responsiveness on-device while keeping data on the user’s PC. It’s a powerful example of the open-ecosystem, holistic design approach we champion to bring energy-efficient intelligence.”
Availability
The LEAP SDK with AMD acceleration is available today, supporting the LFM-2 model families. Developers can explore tools, benchmarks, and documentation at leap.liquid.ai.
Explore AITechPark for the latest advancements in AI, IOT, Cybersecurity, AITech News, and insightful updates from industry experts!