# CarbonScaling: Extending Neural Scaling Laws for Carbon Footprint in Large Language Models

arXiv: https://arxiv.org/abs/2508.06524 · HTML: https://mlsanity.com/paper/2508.06524/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 2 Aug 2025.

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

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM](https://mlsanity.com/paper/2104.04473/) (2021)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [Scalable and Efficient MoE Training for Multitask Multilingual Models](https://mlsanity.com/paper/2109.10465/) (2021)
- [Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training](https://mlsanity.com/paper/2411.13055/) (2024)
- [Coop: Memory is not a Commodity](https://mlsanity.com/paper/2311.00591/) (2023)
- [How Green Can AI Be? A Study of Trends in Machine Learning Environmental Impacts](https://mlsanity.com/paper/2412.17376/) (2024)

## Abstract (arXiv)

Large language models (LLMs) increasingly follow neural scaling laws that tie performance gains to rapidly expanding computational budgets, raising concerns about the sustainability of frontier-scale training. Existing carbon-estimation methods largely depend on regression over historical runs and fail to capture critical system-level factors, including hardware heterogeneity, distributed parallelism, communication overhead, and architectural sparsity. We present textitCarbonScaling, a hardware-aware analytical framework for modeling the carbon scaling behavior of frontier LLM training. The framework integrates neural scaling laws, distributed training strategies, accelerator and interconnect modeling, and operational and embodied carbon accounting to estimate feasible hardware configurations and associated emissions. CarbonScaling jointly models tensor, pipeline, data, and expert parallelism while incorporating memory, bandwidth, utilization, and runtime constraints. Experimental validation demonstrates substantially higher fidelity than regression-based baselines and highlights the growing importance of embodied carbon at trillion-parameter scales. Source code: urlhttps://github.com/UnchartedRLab/CarbonScaling.