Back to Freedom.Tech
Project AI

koboldcpp

koboldcpp, single-binary local LLM runner built on llama.cpp with a built-in chat UI.

12k Stars
755 Forks
12
Releases tracked
GitHub releases
Source type
8 days
Avg cadence
May 2026
First tracked
11d ago
Latest

Release history

AI release Aug 16, 2026

koboldcpp 1.119

Video generation and I2V support with Minimax H3

AI release Aug 1, 2026

koboldcpp 1.118.1

Row Split option removed; Selecting it now defaults to tensor split

AI release Jul 9, 2026

koboldcpp 1.117.1

KoboldCpp 1.117.1 fixes thinking trace display, improves multimodal image placement, adds full Ollama compatibility with embeddings and tool calling, and reworks group chat with multi-character avatars

AI release Jul 9, 2026

koboldcpp 1.117

Fixes terminal output for thinking traces; Multimodal images now inserted inline instead of at context top

AI release Jun 27, 2026

koboldcpp 1.116.1

Koboldcpp 1.116.1 adds Krea 2 Turbo, Ideogram 4, and Boogu Edit image generation models, MCP server support in the web UI, and fixes MTP performance issues

AI release Jun 27, 2026

koboldcpp 1.116

Adds Krea 2 Turbo support

AI release Jun 12, 2026

koboldcpp 1.115.1

Koboldcpp 1.115.1 adds Anthropic API support with multimodal and tool calling, Gemma4 UV models, MTP speculative decoding, video generation improvements, and sampling speedups

AI release Jun 12, 2026

koboldcpp 1.115

Implements full Anthropic /v1/messages API support including multi-turn conversations

AI release May 30, 2026

koboldcpp 1.114.1

Koboldcpp 1.114.1 adds experimental parallel text generation, multi-GPU RPC support, LTX2.3 video generation, and support for Microsoft Lens, HiDream o1, LongCat, and Ernie image models

AI release May 30, 2026

koboldcpp 1.114

Experimental parallel text generation, RPC backend for distributed GPU sharing across networks, LTX2.3 video generation support, and multiple new image generation models added

AI release May 16, 2026

koboldcpp 1.113.1

Breaking change: split mode now set independently to accommodate experimental tensor split. Existing launch scripts may need adjustment

AI release May 16, 2026

koboldcpp 1.113.2

KoboldCpp 1.113.2 fixes router mode regressions, splits tensor configuration independently, adds LoRA directory selection, and improves VAE decoding speed