From Cloud to Keyboard: LEAP Expands to Laptops with Cutting-Edge AMD Ryzen™ Power

Cambridge, MA — August 18, 2025 — 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.” 

The Hardware Fragmentation Challenge

Edge AI deployment faces significant complexity: x86 and ARM architectures, multiple GPU vendors, and three major operating systems (Windows, macOS, Linux) each with distinct requirements. Building native support for every combination would require enormous engineering resources and time.

We're taking a community-first approach. Rather than building everything from scratch, we're partnering with established tools that developers already use in production.

llama.cpp as Our Foundation

Our first integration target is llama.cpp—the de facto standard for efficient inference on consumer hardware. Its mature ecosystem and active community have already solved many critical optimization challenges.

By supporting llama.cpp as our inference engine, LEAP integrates seamlessly into existing workflows:

• Python developers can use our bindings alongside their current toolchain
• Node.js developers get native performance without C++ complexity
• The entire llama.cpp ecosystem of tools and optimizations works immediately

After extensive benchmarking across consumer hardware, AMD Ryzen AI processors deliver the best performance for LEAP deployments. In Figure 1, we compare the performance measure in tokens per second (higher is better) for both prefill (prompt-processing) and decode (token generation) operations of LFM2-1.2B-Q4_0.gguf. For a fair comparison we use the publicly released `llama-bench` executables from the main llama.cpp GitHub repository with all available pre-built backends, including all available GPU backends, as well as for the CPU backend we vary the number of threads (4, 8, and 12), and report the maximum values observed for each hardware.

Integrated Radeon Graphics for Prompt Processing

The integrated GPU handles prompt processing at speeds comparable to discrete GPUs—without additional cost, power draw, or integration complexity. This enables genuinely real-time application experiences.

Superior CPU Decode Performance

Token generation leverages AMD's Zen 5 architecture with advanced vector instruction sets, delivering some of the fastest decode/generation speeds measured on consumer hardware. This combination provides GPU acceleration for prompt processing and optimized CPU performance for streaming generation—all in a single chip that's already deployed in millions of devices.

Building with LEAP

With LEAP running locally via llama.cpp on AMD hardware, developers can now build:

• Privacy-first applications where sensitive data remains on-device
• Real-time AI features with consistent sub-100ms latency
• 100% local software that functions without internet connectivity
• Cost-effective solutions eliminating cloud inference expenses

The same code runs wherever llama.cpp is supported, ensuring no vendor lock-in.

Getting Started

We've created comprehensive documentation on our LEAP platform covering:

1. Installing LEAP with llama.cpp backend
2. Loading and running LFM-2 models
3. Integration with Python and Node.js applications
4. Performance optimization for AMD Ryzen hardware

The SDK is available today with benchmarks and example implementations.

What's Next

This AMD integration represents the first step in making powerful AI ubiquitous on edge devices. Our immediate roadmap includes:

• LFM-2-VL support: Bringing our vision-language models to edge devices, enabling multimodal applications that process both text and images locally
• Further memory and power optimizations, leveraging GPUs and NPUs
• Integration with additional inference engines beyond llama.cpp

The future of AI extends beyond data centers to the devices your users already own. We're building the infrastructure to make that future accessible to every developer.

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.

How to Get Started 

If you are interested in custom solutions with edge deployment, please contact our sales team at sales@liquid.ai.

Try LFM2 on

Liquid Playground

llama.cpp

Hugging Face