KoboldCpp

One-file llama.cpp build with a built-in chat UI aimed at offline storytelling.

Install Repository Compare

Fit.

Catalog snapshot

Platforms: Linux, Macos, Windows
Operating systems: Linux, macOS, Windows
Ram floor: 8 GB
Gpu: Optional · 6 GB VRAM helps
Docker: No
Setup: Beginner
Deploy as: Local
Commercial use: Check the license

AGPL. Runs 7B quantized on 8 GB RAM, slowly without a GPU.

Project.

Fetched Sep 12, 2026¹

License: AGPL-3.0
Stars: 11.7k¹
Forks: 761¹
Open issues: 509¹
Language: C++¹
Last commit: Sep 9, 2026¹
Latest release: Aug 28, 2026
Tags: ggufsingle-filewindows

About.

KoboldCpp is llama.cpp plus a classic storytelling UI in one file you double-click. It is the least-fuss Windows path to offline GGUF chat. AGPL and the dated UI are the trade-offs.

single executable · KoboldAI UI · GGUF · CPU inference

Alternatives.

Nearby.

All Local AI

LllamafileSingle-file LLM runtime from Mozilla. Download, chmod, run.Compare
GgptmeMIT terminal agent toolkit with code, shell, and web tools — local-model friendly.Compare
GGPT4AllNomic’s local chat app and model catalog for laptops without a GPU.Compare
Ttext-generation-webuiGradio UI for local models with loaders, LoRA, and extensions.Compare
FFlowiseLow-code node UI on top of LangChain-style flows.Compare