The transition of Large Language Models (LLMs) from centralized clouds to edge environments is critical for addressing privacy concerns, latency bottlenecks, and operational costs. However, existing edge benchmarking frameworks remain tailored to discriminative Deep Learning tasks (e.g., object detection), failing to capture the multidimensional challenges of generative AI, specifically the trade-offs between token generation speed, semantic accuracy, and hardware sustainability. To address this gap, we introduce LEAF (LLM Edge Assessment Framework), a novel evaluation methodology that integrates Circular Economy principles directly into performance metrics. LEAF assesses edge deployments across five synergistic pillars: Circular Economy Score, Energy Efficiency (Joules/Token), Performance Speed (Tokens/Second), semantic accuracy (BERTScore), and End-to-End Latency. We validate LEAF through an extensive experimental analysis of five distinct hardware classes, ranging from embedded IoT devices (Raspberry Pi 4 and 5, NVIDIA Jetson Nano) to professional edge servers (NVIDIA T400) and repurposed legacy workstations (NVIDIA GTX 1050 Ti). Utilizing 4-bit quantized models via the Ollama runtime, our results reveal a counterintuitive insight: repurposed consumer hardware significantly outperforms modern purpose-built edge SoCs. The legacy GTX 1050 Ti achieved a 20× speedup over the Raspberry Pi 4 and maintained superior energy-per-task efficiency compared to low-power ARM architectures by minimizing active runtime. These findings challenge the prevailing narrative that newer silicon is essential for Edge AI, demonstrating that sustainable, high-performance inference can be achieved by extending the lifecycle of existing hardware. LEAF thus provides a blueprint for a “Green Edge” ecosystem that balances computational capability with environmental responsibility.

Edge computing is characterized by heterogeneous hardware, distributed deployment, and a need for on-site processing, which makes performance benchmarking challenging. This paper presents SHEAB (Scalable Heterogeneous Edge Automation Benchmarking), a novel framework designed to securely automate the benchmarking of Edge AI devices at scale. The proposed framework enables concurrent performance evaluation of multiple edge nodes, drastically reducing the time-to-deploy (TTD) for benchmarking tasks compared to traditional sequential methods. SHEAB’s architecture leverages containerized microservices for orchestration and result aggregation, integrated with multi-layer security (firewalls, VPN tunneling, and SSH) to ensure safe operation in untrusted network environments. We provide a detailed system design and workflow, including algorithmic pseudocode for the SHEAB process. A comprehensive comparative review of related work highlights how SHEAB advances the state-of-the-art in edge benchmarking through its combination of secure automation and scalability. We detail a real-world implementation on eleven heterogeneous edge devices, using a centralized 48-core server to coordinate benchmarks. Statistical analysis of the experimental results demonstrates a 43.74% reduction in total benchmarking time and a 1.78× speedup in benchmarking throughput using SHEAB, relative to conventional one-by-one benchmarking. We also present mathematical formulations for performance gain and discuss the implications of our results. The framework’s effectiveness is validated through the concurrent execution of standard benchmarking workloads on distributed edge nodes, with results stored in a central database for analysis. SHEAB thus represents a significant step toward efficient and reproducible Edge AI performance evaluation. Future work will extend the framework to broader workloads and further improve parallel efficiency.

The use of Deep Neural Networks (DNNs) on autonomous Internet of Things (IoT) devices is bottlenecked and causes accelerated battery degradation, memory exhaustion and thermal throttling due to constant inference demands. While the current literature largely deals with this through static model quantization, in this paper, FuzzPrismEdge, an adaptive 3-tier hybrid fuzzy-neural architecture that dynamically scales computational payloads according to real-time environmental context is introduced. Using a lightweight Fuzzy Logic Controller (FLC) as a preliminary hardware gatekeeper, the framework assesses ambient telemetry; namely energy reserves and intensity of motion, to dynamically steer system states based on crisp defuzzified thresholds. In order to eliminate redundant spatial processing FuzzPrismEdge uses dynamic model substitution: Low-priority telemetry causes a deep hardware sleep (Tier 1), moderate telemetry triggers a lightweight spatial classifier (Tier 2), and critical telemetry triggers a computationally intensive, heavyweight object detection model (Tier 3). By dynamically allocating DNN complexity based on event priority, the FuzzPrismEdge architecture actively conserves the allocation of RAM, avoids unnecessary GPU spin-up in non-critical events, and extends the autonomous operational lifespan of edge nodes by 60.0% to 66.7% compared to static unoptimized baselines.