# Greening Large Language Models of Code

arXiv: https://arxiv.org/abs/2309.04076 · HTML: https://mlsanity.com/paper/2309.04076/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2023.

## Built on by (most cited first, 19 of 19)

- [Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency](https://mlsanity.com/paper/2504.03360/) (2025)
- [How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering](https://mlsanity.com/paper/2501.08774/) (2025)
- [A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models](https://mlsanity.com/paper/2507.22659/) (2025)
- [LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs](https://mlsanity.com/paper/2505.24451/) (2025)
- ["My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants](https://mlsanity.com/paper/2508.12285/) (2025)
- [CodeCipher: Learning to Obfuscate Source Code Against LLMs](https://mlsanity.com/paper/2410.05797/) (2024)
- [On the Compression of Language Models for Code: An Empirical Study on CodeBERT](https://mlsanity.com/paper/2412.13737/) (2024)
- [Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights](https://mlsanity.com/paper/2504.06307/) (2025)
- [An Empirical Study of Knowledge Distillation for Code Understanding Tasks](https://mlsanity.com/paper/2508.15423/) (2025)
- [FairSense-AI: Responsible AI Meets Sustainability](https://mlsanity.com/paper/2503.02865/) (2025)
- [Evaluating Useful Surrogate Models for Configuration Tuning Beyond Accuracy: A Fitness Landscape Analysis Perspective](https://mlsanity.com/paper/2509.21945/) (2025)
- [A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?](https://mlsanity.com/paper/2511.05476/) (2025)
- [Insights into resource utilization of code small language models serving with runtime engines and execution providers](https://mlsanity.com/paper/2412.15441/) (2024)
- [Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization](https://mlsanity.com/paper/2508.02840/) (2025)
- [Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models](https://mlsanity.com/paper/2604.25903/) (2026)
- [Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection](https://mlsanity.com/paper/2605.02860/) (2026)
- [Quantize with Confidence? An Empirical Study of Quantization for Code Generation](https://mlsanity.com/paper/2607.14181/) (2026)
- [FLOPs vs Real Work: The Importance of Replication in AI Efficiency Assessment](https://mlsanity.com/paper/2608.14550/) (2026)
- [Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Task](https://mlsanity.com/paper/2608.17515/) (2026)

## Abstract (arXiv)

Large language models of code have shown remarkable effectiveness across various software engineering tasks. Despite the availability of many cloud services built upon these powerful models, there remain several scenarios where developers cannot take full advantage of them, stemming from factors such as restricted or unreliable internet access, institutional privacy policies that prohibit external transmission of code to third-party vendors, and more. Therefore, developing a compact, efficient, and yet energy-saving model for deployment on developers' devices becomes essential. To this aim, we propose Avatar, a novel approach that crafts a deployable model from a large language model of code by optimizing it in terms of model size, inference latency, energy consumption, and carbon footprint while maintaining a comparable level of effectiveness. The key idea of Avatar is to formulate the optimization of language models as a multi-objective configuration tuning problem and solve it with the help of a Satisfiability Modulo Theories (SMT) solver and a tailored optimization algorithm. The SMT solver is used to form an appropriate configuration space, while the optimization algorithm identifies the Pareto-optimal set of configurations for training the optimized models using knowledge distillation. We evaluate Avatar with two popular language models of code, i.e., CodeBERT and GraphCodeBERT, on two popular tasks, i.e., vulnerability prediction and clone detection. We use Avatar to produce optimized models with a small size (3 MB), which is 160× smaller than the original large models. On the two tasks, the optimized models significantly reduce the energy consumption (up to 184× less), carbon footprint (up to 157× less), and inference latency (up to 76× faster), with only a negligible loss in effectiveness (1.67% on average).