MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUs

Evolutionary model merging enables the creation of high-performing multi-task models but remains computationally prohibitive for consumer hardware. We introduce MERGE$^3$, an efficient framework that makes evolutionary merging of Large Language Models (LLMs) feasible on a single GPU by reducing fitness computation costs 50$\times$ while retaining a large fraction of the original performance. MERGE$^3$ achieves this by E xtracting a reduced dataset for evaluation, E stimating model abilities using Item Response Theory (IRT), and E volving optimal merges via IRT-based performance estimators. Our method enables state-of-the-art multilingual and cross-lingual merging, transferring knowledge across languages with significantly lower computational overhead. We provide theoretical guarantees and an open-source library, democratizing high-quality model merging.

Authors

• Tommaso Mencattini
• Adrian Robert Minut
• Donato Crisostomi
• Andrea Santilli
• Emanuele Rodolà

Keywords

• Model Merging
• Evolutionary Algorithms
• Efficient Methods for Machine Learning
• Language Models
• LLMs
• Multilingual Models