Now accepting early-access sign-ups

The Definitive Hub for Model Merging

An independent, community-driven registry for merge recipes, interactive Merge Map visualizers, and specialized leaderboards — everything you need to discover, share, and benchmark merged models in one place.

Get early access + a free Top 50 Merge Recipes PDF. No spam, ever.

2,400+

Recipes indexed

180+

Contributors

50+

Merge methods

Core Platform

Everything the community needs — in one place

Stop jumping between scattered repos, spreadsheets, and Discord threads. MergeKit brings the essential infrastructure together.

Recipe Registry

A centralized, searchable catalog of community-contributed merge recipes. Filter by method, base model, benchmark score, or popularity — and publish your own in seconds.

Merge Map Visualizer

Explore the lineage and layer-level composition of any merged model through interactive node graphs. Trace weight flows, identify shared ancestors, and understand merge topology at a glance.

Specialized Leaderboards

Purpose-built rankings for merged models — not just overall scores. Compare across task-specific, safety, efficiency, and community-voted dimensions with transparent methodology.

Merge Map Visualizer

See how models are actually built

Every merged model has a hidden family tree. Our interactive Merge Maps let you zoom into layer-level detail, trace parameter flows, and instantly spot which source models contributed what.

  • Interactive node-graph exploration
  • Layer-level weight contribution heatmaps
  • Ancestor model lineage tracing
  • Exportable SVG & JSON diagrams
merge-map://WizardLM-2-Merged
Llama-3-70B
CodeLlama-34B
SLERP 0.6
TIES 0.4
Linear Merge
WizardLM-2-Merged
Merged Model Leaderboard
#ModelScore
1NeuralMerge-70B-v289.4+3.2
2SynthWizard-34B87.1+1.8
3MegaCode-Instruct86.7+0.5
4AlphaChat-13B-Mix85.2-0.3
5OmniMerge-7B84.8+2.1
Updated daily · Transparent evaluation methodology

Specialized Leaderboards

Rankings built for merged models

Generic leaderboards bury merged models alongside base models. Ours are purpose-built with dimensions that actually matter — safety, code, reasoning, instruction-following, and community-voted categories.

  • Task-specific dimension rankings
  • Transparent, reproducible eval methodology
  • Daily automated re-evaluation
  • Community-nominated benchmark categories

Get early access & the Top 50 Merge Recipes

Join the waitlist for priority access to the registry, visualizer, and leaderboards. As a thank-you, we'll send you a curated PDF of the 50 highest-impact merge recipes — method, config, and benchmark results included.

Join the Waitlist

Free forever during beta · No credit card · Unsubscribe anytime

Privacy-firstCommunity-drivenOpen methodology