Kobold.cpp
Easy-to-use local AI inference with built-in web UI and API.
About
Kobold.cpp is a single-file local AI inference solution with a built-in web UI for chat and story generation. Based on llama.cpp with additional features like GPU offloading, context shifting, and image generation. Supports GGUF models. AGPL-3.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- LLM Inference & Serving
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Beginner (1/5)
- License
- AGPL-3.0
- Added
- Apr 3, 2026
Related Tools
Port of Meta's LLaMA model in C/C++ for efficient CPU inference
High-throughput LLM serving engine with PagedAttention
Minimalist ML framework in Rust by Hugging Face for fast inference.
Optimized inference library for running quantized LLMs on consumer GPUs.
Open-source ChatGPT alternative that runs 100% offline on your computer.
Fast LLM inference on consumer GPUs using neuron-aware sparse computation.