# CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices

arXiv: https://arxiv.org/abs/2504.20348 · HTML: https://mlsanity.com/paper/2504.20348/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 12 of 12)

- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [TinyAgent: Function Calling at the Edge](https://mlsanity.com/paper/2409.00608/) (2024)
- [LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error](https://mlsanity.com/paper/2403.04746/) (2024)
- [Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service](https://mlsanity.com/paper/2304.09781/) (2023)
- [GreenScale: Carbon-Aware Systems for Edge Computing](https://mlsanity.com/paper/2304.00404/) (2023)
- [LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching](https://mlsanity.com/paper/2406.06799/) (2024)

## Built on by (most cited first, 1 of 1)

- [Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systems](https://mlsanity.com/paper/2609.13559/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) enable real-time function calling in edge AI systems but introduce significant computational overhead, leading to high power consumption and carbon emissions. Existing methods optimize for performance while neglecting sustainability, making them inefficient for energy-constrained environments. We introduce CarbonCall, a sustainability-aware function-calling framework that integrates dynamic tool selection, carbon-aware execution, and quantized LLM adaptation. CarbonCall adjusts power thresholds based on real-time carbon intensity forecasts and switches between model variants to sustain high tokens-per-second throughput under power constraints. Experiments on an NVIDIA Jetson AGX Orin show that CarbonCall reduces carbon emissions by up to 52%, power consumption by 30%, and execution time by 30%, while maintaining high efficiency.