# What is Model merging? Definition and meaning

Model merging creates a new model by combining the weights of two or more existing models, usually fine-tuned from the same base, without further gradient training.

## Definition

**Model merging**: Model merging creates a new model by combining the weights of two or more existing models, usually fine-tuned from the same base, without further gradient training.

In short: Blend models without retraining.

## When it is used

Combining skills from separate fine-tunes, improving robustness, building open-weight LLM variants and cheaply exploring model combinations.

## Where it fits

Model merging belongs to **Frontier topics** in the [Generative AI and LLMs](/topics/generative-ai-llms) topic. These are the other terms in the same group:

- **[Test-time compute](/glossary/test-time-compute)**: Test-time compute is the extra computation a model spends while answering a single request, used to raise the quality of that answer.
- **[Diffusion language models](/glossary/diffusion-language-models)**: A diffusion language model generates text by iteratively denoising a whole sequence, usually by filling in masked tokens over several steps, instead of predicting one token at a time from left to right.
- **[Prompt caching](/glossary/prompt-caching)**: Prompt caching reuses the already-computed internal state for an identical prompt prefix across requests, so only the new part of each prompt has to be processed.
- **[LLM routing](/glossary/llm-routing)**: LLM routing is the practice of choosing, for each incoming request, which language model or configuration should handle it.
- **[AI watermarking and provenance](/glossary/ai-watermarking-and-provenance)**: Techniques that embed a hidden, detectable signal in AI-generated content, or attach signed records of its origin, so it can later be identified.

## Learn more

The full guide to **[Model merging](/tools/model-merging)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Model cards](/glossary/model-cards) · Next term: [Model monitoring](/glossary/model-monitoring)
