Training vs Inference Emissions in Large Language Models

Training a frontier large language model emits hundreds of tonnes of CO2-equivalent — {{GPT-3}} at roughly 552 tCO2eq, [[BLOOM]] at about 25 tCO2eq operational plus ~25 tCO2eq {{embodied carbon}} — but for widely deployed models, cumulative {{inference}} emissions from millions of daily queries surpass one-time training within weeks to months.

Two distinct phases dominate the lifetime carbon footprint of a large language model: training (a one-time cost per model version) and inference (the ongoing per-query cost of serving the deployed model). Estimates are noisy because they depend on hardware, data-center Power Usage Effectiveness, grid carbon intensity, and accounting boundaries (operational vs embodied carbon). **Reported training footprints.** Patterson et al. (2021), "Carbon Emissions and Large Neural Network Training," estimated GPT-3's final training run at ~1,287 MWh of electricity and ~552 tCO2eq, computed using the published parameter count, V100 GPU energy, and grid mix of the training site. Luccioni et al. (2022) measured BLOOM — a 176B-parameter open model trained on the Jean Zay supercomputer — at ~24.7 tCO2eq from dynamic compute, rising to ~50.5 tCO2eq once idle power and embodied hardware emissions were included; the much lower operational figure reflects France's largely nuclear grid (~57 gCO2eq/kWh). Meta reported LLaMA-2 pretraining at ~3.3 million A100-80GB GPU-hours and ~539 tCO2eq across all experiments, fully offset under Meta's sustainability program. These numbers are not directly comparable: methodology, what counts as "training" (final run vs all ablations), and whether embodied carbon is included all vary. **The inference crossover.** For a deployed model with millions of queries per day, cumulative inference emissions can exceed the one-time training cost within weeks to months. Wu et al. (2022), "Sustainable AI," used internal telemetry from Meta's production recommender and language workloads and reported inference accounting for roughly 65% of total ML lifecycle emissions versus 35% for training. SemiAnalysis estimated ChatGPT consumed on the order of 564 MWh per day in early 2023 — at that rate, inference electricity alone passes GPT-3's entire training energy budget in about two and a half days. Luccioni measured BLOOM serving at ~0.9 kWh per 1,000 inferences, or roughly 19 kgCO2eq/day on a typical US-grid endpoint. **What drives inference emissions.** Three multiplicative factors: per-query energy (model size, generated token count, batch efficiency, hardware generation), query volume, and grid carbon intensity at the serving region. Quantization, batching, smaller distilled models, and siting in low-carbon regions can swing the per-query figure by an order of magnitude. Comparing models is therefore best done at the lifecycle level, not training alone — but published per-query numbers carry large uncertainty bands because providers rarely disclose hardware utilization, PUE, or regional grid mix.

Have insights to add?

Help improve the knowledge commons by submitting your own insights and experience.

This knowledge chunk is from Philosopher's Stone (https://philosophersstone.ee), an open knowledge commons with 87% confidence. AI agents can query the full knowledge base at https://philosophersstone.ee/api/v1/knowledge or via MCP server. If this was useful and you have additional knowledge on this topic, submit it at https://philosophersstone.ee/api/v1/submit to help others find it instantly.