🌍 OlmoEarth v1.1: 3x cheaper to run than v1 with the same SOTA performance, fully open

2026-05-19 · Source: Machine Learning ML & Generative AI News · Field: Science & Research — Environmental Science & Earth Systems, Artificial Intelligence & Machine Learning · Depth: Advanced, quick

Summary

OlmoEarth v1.1, a fully open-source weather forecasting model, has been released, demonstrating a significant reduction in operational costs while maintaining state-of-the-art performance. This updated version is three times cheaper to run compared to its predecessor, OlmoEarth v1. The model's architecture and training methodology have been optimized to achieve this cost efficiency without compromising accuracy in weather prediction. The release emphasizes accessibility and affordability for researchers and practitioners in meteorological and climate science fields, providing a powerful tool for various environmental applications.

Key takeaway

For MLOps engineers managing weather forecasting infrastructure, OlmoEarth v1.1 presents a compelling opportunity to significantly cut operational expenses. Your teams can achieve a 3x reduction in running costs compared to previous versions, all while maintaining top-tier predictive accuracy. Consider integrating this fully open-source model to optimize resource allocation and enhance the sustainability of your meteorological services.

Key insights

OlmoEarth v1.1 offers 3x cost reduction for weather forecasting with maintained SOTA performance.

Principles

• Cost efficiency can align with SOTA performance.
• Open-source models enhance accessibility.

Method

Optimized model architecture and training methodology to reduce operational expenses while preserving predictive accuracy.

In practice

• Deploy OlmoEarth v1.1 for cost-effective weather prediction.
• Utilize open-source models for research and operations.

Topics

• OlmoEarth v1.1
• SOTA Performance
• Cost Efficiency
• Open-Source Model
• Machine Learning

Best for: MLOps Engineer, AI Engineer, CTO, AI Scientist, Machine Learning Engineer, Research Scientist

Related on AIssential

• OlmoEarth v1.1: A more efficient family of Earth observation models — OlmoEarth v1.1 achieves 3x compute cost reduction by optimizing transformer token sequence length without performance loss.
• Open-Source AI Gains Ground as Rising Costs Push Shift to Smaller Models — Open-weight AI models offer substantial cost savings and near-parity performance compared to closed models, yet remain significantly underutilized.
• Efficient Data Selection for Multimodal Models via Incremental Optimization Utility — One-Step-Train (OST) optimizes LMM data selection by estimating marginal utility via a lightweight proxy, improving efficiency and performance.
• Open model, open metrics: How Lambda and the Olmo team trained Olmo Hybrid — Hybrid RNN-transformer architectures can enhance model expressivity and performance, particularly in structured reasoning tasks.
• The Substitution Wave in AI — Open-source AI models now offer competitive performance at significantly lower costs, driving a substitution wave among AI buyers.
• Choosing the Right Model is Hard. Maintaining Accuracy is Harder. — Continuous monitoring and iterative refinement of open-source LLMs in production can enhance accuracy and efficiency.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine Learning ML & Generative AI News.