Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

A high-throughput and memory-efficient inference and serving engine for LLMs

軽量で規制も検閲もない日本語ローカル LLM『LightChatAssistant-TypeB』による、簡単なノベル生成アシスタントです。ローカル特権の永続生成 Generate forever で、当たりガチャを積み上げます。読み上げにも対応。

LLM Frontend for Power Users.

Stable Diffusion built-in to Blender

Multi-Platform Package Manager for Stable Diffusion

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

An OAI compatible exllamav2 API that's both lightweight and fast

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.