Hugging Face· PlatformStory of the weekResearch paper

CO₂ Emissions and Models Performance: Insights from the Open LLM Leaderboard

Hugging Face published a blog post analyzing CO₂ emissions and performance of over 3,000 models on the Open LLM Leaderboard, integrating carbon emission estimates to promote transparency and environmental responsibility. The post finds that larger models generally have higher CO₂ costs with diminishing returns, and that community fine-tunes tend to be more carbon-efficient than official models.

From the source

By integrating carbon emission estimates into the Open LLM Leaderboard, we aim to provide transparency to users about the carbon impact of various model evaluations and hopefully encourage model creators to balance performance with environmental responsibility.

huggingface.co