November 11, 2026 -

New development toolkit streamlines the journey from trained AI models to optimized, deployable embedded applications, with automated firmware generation, RISC-V integration, and comprehensive performance analytics.

BARCELONA, SPAIN – INTERA Group, a semiconductor technology company specializing in configurable Edge AI accelerator IP and embedded intelligence solutions, today announced the launch of its INTERA TinyML Toolkit, a software development solution designed to simplify and accelerate the deployment, optimization, and benchmarking of artificial intelligence models on resource-constrained embedded hardware.

As demand for intelligent, low-power edge devices continues to grow across industrial, automotive, IoT, and embedded computing applications, developers face increasing challenges in transitioning AI models from training environments to production-ready hardware implementations. INTERA’s TinyML Toolkit addresses these challenges by providing an integrated workflow that automates critical development stages, reduces manual integration effort, and enables systematic evaluation of AI inference performance.

Bridging the Gap Between AI Development and Embedded Deployment

The INTERA TinyML Toolkit transforms trained TensorFlow and Keras models into deployable embedded applications through a streamlined six-stage workflow: Convert, Generate, Benchmark, Build, Deploy, and Analyze.

The toolkit automatically converts and quantizes AI models into TensorFlow Lite format, generates TensorFlow Lite Micro projects, creates embedded firmware and benchmarking infrastructure, compiles applications for RISC-V targets, and deploys workloads to supported hardware platforms.

Once deployed, developers can evaluate inference execution using detailed analytics covering memory footprint, execution cycles, latency, layer-level performance, and hardware accelerator efficiency. This unified approach enables engineering teams to move from model development to hardware validation through a more reproducible and measurable process.

Designed for INTERA’s Cognit AI Accelerator Portfolio

A key differentiator of the TinyML Toolkit is its integration with INTERA’s Cognit family of configurable AI accelerator IP, enabling developers to evaluate and optimize AI workloads across different computing architectures. The toolkit supports five INTERA accelerator technologies:

• Falcon Cognit: Monolithic streaming accelerator optimized for efficient matrix-vector computations.
• Hawk Advance Cognit: RISC-V-based accelerator featuring custom instructions and scalable matrix operations.
• Hawk Pro Cognit: High-performance, configurable RISC-V-based AI acceleration architecture.
• Eagle Cognit: Near-memory computing accelerator designed for high energy efficiency.
• Harrier Cognit: Monolithic accelerator supporting scalable matrix-matrix computations.

Through accelerator-aware model optimization, integer-quantized execution, and integrated benchmarking, the toolkit allows developers to compare hardware-accelerated inference against baseline CPU implementations. This capability supports informed architectural decisions, helping engineering teams evaluate performance, memory utilization, and computational efficiency before committing to a particular hardware configuration.

Comprehensive Development and Performance Analysis

The INTERA TinyML Toolkit combines several essential capabilities in a single development environment:

• AI Model Optimization: Support for TensorFlow and Keras models, multiple quantization approaches, and neural network architectures including CNN, FCNN, MLP, RNN, LSTM, and GRU.
• Automated Firmware Generation: TensorFlow Lite Micro runtime integration, automatic C model generation, benchmarking scaffolding, and configurable memory allocation.

• Embedded Hardware Deployment: RISC-V toolchain integration, FPGA and SoC deployment support, automated build and flashing, and OpenOCD/GDB debugging capabilities.
• Performance Analytics: Detailed HTML reporting, layer-by-layer profiling, cycle counting, memory analysis, and hardware accelerator versus CPU performance comparisons.

Together, these capabilities provide developers with a consistent framework for evaluating TinyML applications, validating accelerator architectures, and preparing embedded AI implementations for further product development.

Enabling the Next Generation of Edge AI Applications

The INTERA TinyML Toolkit is designed to support semiconductor developers, embedded software engineers, AI researchers, and product development teams working on intelligent edge devices. Potential applications include industrial predictive maintenance, intelligent sensing, autonomous systems, robotics, wearable electronics, and battery-powered IoT devices, where computational efficiency and predictable execution performance are particularly important.

By connecting software model development with measurable hardware execution, INTERA aims to make advanced Edge AI technologies more accessible and easier to integrate into embedded computing systems.

Advancing INTERA’s Vision for Configurable Edge AI

The launch of the TinyML Toolkit strengthens INTERA’s broader technology offering by complementing its configurable semiconductor IP portfolio with software tools that support model deployment, hardware evaluation, and development workflows. The combination of configurable AI acceleration hardware and integrated software development capabilities reinforces INTERA’s objective of enabling flexible, efficient, and application-specific Edge AI solutions.

With the TinyML Toolkit, INTERA continues expanding its semiconductor technology ecosystem, helping customers bridge the gap between AI algorithms, embedded software, and hardware acceleration.

About INTERA Group

INTERA Group is a European semiconductor technology company focused on developing configurable semiconductor IP, Edge AI acceleration technologies, and customized ASIC and FPGA solutions. Through its Cognit family of AI accelerator IP and complementary software development technologies, INTERA enables the integration of intelligent processing capabilities into embedded systems and next-generation semiconductor platforms. The company is committed to advancing flexible, energy-efficient, and sovereign European semiconductor technologies for industrial, commercial, and strategic applications.