# arcee-ai/mergekit

Tools for merging pretrained large language models.

Repository: https://github.com/arcee-ai/mergekit
Canonical: https://ross.abutalabs.com/products/mergekit
Language: Python
License: LGPL-3.0
License Family: copyleft
Topics: llama, llm, model-merging
Last push: 2026-06-17T20:51:27+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 88, release rhythm 22, longevity 79
- inputs: {"age_days": 1108, "days_push": 77, "days_rel": 306, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7310, forks 785 (observed 2026-08-28T04:09:58.144500+00:00)

## What it is
mergekit is a Python toolkit for merging pre-trained large language models directly in weight space, supporting many merge methods (SLERP, TIES, DARE, MoE merging, evolutionary merges) with an out-of-core approach that runs on CPU or minimal GPU memory. It includes companion tools for LoRA extraction, raw PyTorch merging, tokenizer transplantation, and multi-stage merges.

## Use cases
- merge two fine-tuned llama models into one
- combine strengths of multiple LLMs without training
- create a mixture-of-experts model from existing checkpoints
- merge language models on a low-VRAM GPU
- extract a LoRA adapter from a merged model
- transfer capabilities between models without training data
- transplant tokenizer between language models

## When to choose
- you want to combine pretrained LLM checkpoints without additional training
- you have limited GPU memory and need out-of-core merging
- you want to experiment with many merge algorithms (SLERP, TIES, DARE, evolutionary)
- you work with Llama, Mistral, GPT-NeoX, or similar architectures

## When to avoid
- you need to train or fine-tune a model from scratch rather than merge existing ones
- your models have incompatible architectures or vastly different tokenizers without using the specialized tools
- you need a managed GUI service rather than a config-driven CLI toolkit

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-training, sdk, cli
- domain: large-language-models, machine-learning, deep-learning, developer-tools
- platform: python, cli, cross-platform
- tags: model-merging, llm, model-fusion, moe, lora, weight-space-merging, huggingface, gpu

## Member repositories
- arcee-ai/mergekit (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:58.144500+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:38:40.901404+00:00, confidence not recorded.
  - readme: https://github.com/arcee-ai/mergekit (fetched 2026-08-28T04:09:58.144500+00:00, sha 82676eda14f0)
- Data as of 2026-08-30T08:39:29.467469+00:00.