KoboldCpp

A single-file local model server built for storytelling and roleplay, with the sampler controls that community actually uses.

At a glance

Where it runs
Self-hostedYou run it on your own machine. Nothing leaves it unless you send it.
Adult content
AllowedAdult content is permitted within the published rules.
Trains on your content
NoYour content is not used to train models.
Status
ActiveMaintained and working today.
Account needed
No
Licence
AGPL-3.0
Cost
Free and open source.
What it keeps
Local only.

What it takes to run

Graphics memory
No GPU needed
System memory
8 GB, 16 GB recommended
Disk
about 10 GB
Runs on
Linux, macOS, Windows

Find what fits your machine on the tools page — pick your hardware from the first menu.

One executable, no installer, no Python environment. It loads a GGUF file and serves both its own writing-focused interface and the APIs that SillyTavern and friends expect.

Where Ollama optimises for the shortest path to a chatbot, KoboldCpp optimises for the person who wants to tune repetition penalty and context shifting at three in the morning. It is the usual backend recommendation in the roleplay community for exactly that reason.

Worth knowing before you start

What it does

Models it runs

How it relates to other tools

Signs of life

Checked automatically. These are the only figures on this page a machine wrote, and they say when they were taken.

Last answered
Yes, 3 hours ago Its website responded when we asked.
Stars on GitHub
11,721 768 forks.
Last commit
4 hours ago2026-09-16 01:49 UTC
Latest release
v1.121
Archived copy
Wayback Machine A snapshot, in case this one stops answering.

Categories

Something here wrong or out of date? Tell us — this page is only worth having if it is right.