Home › Directory › Local Inference › KoboldCpp

KoboldCpp

Single-file llama.cpp distribution with API.

Visit KoboldCpp Docs

Category	Local Inference
Authentication	No auth
Pricing	Free
Website	https://github.com/LostRuins/koboldcpp
Docs	https://github.com/LostRuins/koboldcpp/wiki
Last checked	2026-10-14
As JSON	/api/v1/directory/koboldcpp.json

Information is summarised in our own words and may be out of date; check the vendor's site for current terms and prices. Not affiliated with KoboldCpp. Suggest a correction.

More in Local Inference

llama.cpp

C/C++ LLM inference with an OpenAI-compatible server.

Llamafile

Single-file executable LLMs.

MLX

Apple's array framework for ML on Apple silicon.

Cortex

Local AI engine from Jan.