LLM Perks

KoboldCpp

LostRuins (Concedo) · Local LLM runners
Open sourceBYOKOpenAI API★ 11.8K

Single-file llama.cpp-based runner with the KoboldAI Lite UI; OpenAI/Ollama-compatible APIs plus image generation, Whisper and TTS.

License
AGPL-3.0
Platforms
Windows, macOS, Linux, Docker, CLI
Own API keys
Yes
Checked
2026-09-24
Connect a free model

KoboldCpp works with OpenAI-compatible APIs. Grab a free key and a model from the catalog: for coding · for agents · providers and base URLs

KoboldCpp alternatives

Ollama
Ollama Inc.

Popular runtime to download and run open LLMs locally via CLI, desktop app and a REST/OpenAI-compatible API.

Open sourceBYOK★ 182K
LM Studio
Element Labs

Desktop app to discover, download and run local LLMs (llama.cpp, MLX) with a chat UI and an OpenAI-compatible local server.

FreeBYOK
Jan
Menlo Research

Offline ChatGPT alternative: runs local LLMs, connects to cloud APIs, supports MCP and serves an OpenAI-compatible API on localhost.

Open sourceBYOK★ 44.6K
llama.cpp
ggml-org

Reference C/C++ engine for GGUF models; llama-server provides an OpenAI-compatible API and web UI on CPU, CUDA, Metal, Vulkan and ROCm.

Open sourceBYOK★ 129K
vLLM
vLLM Project

High-throughput LLM inference and serving engine with an OpenAI-compatible server for NVIDIA, AMD, Intel, TPU and CPU.

Open sourceBYOK★ 92.5K
LocalAI
Ettore Di Giacinto & community

Self-hosted drop-in OpenAI/Anthropic API replacement for LLMs, images, audio, video and embeddings on CPU or GPU.

Open sourceBYOK★ 49.2K

FAQ

Is KoboldCpp free?

Completely free and open source, distributed as a single executable with no install.

Does KoboldCpp work with free models?

Yes. It supports your own keys and OpenAI-compatible APIs, so you can plug in free models from OpenRouter, Groq, NVIDIA Build, or a local Ollama.

What license does KoboldCpp use?

AGPL-3.0. The source code is open.