4d-llm

Gemma 4 in GGUF

oxibonsai is a pure Rust inference engine for PrismML’s Bonsai family.

Local inference engine

llama.cpp is an open-source C/C++ library and CLI tool for running large language models (LLMs) locally on consumer hardware. This component provides a class-based generic API with callback functions to use llama.cpp from 4D.

Local inference engine

Uzu is a high-performance inference engine for AI models. It allows you to deploy AI directly in your app with zero latency, full data privacy, and no inference costs.

TranslateGemma in GGUF, ONNX

NLLB in CT2

Local inference engine

FLAN T5 in CT2

CTranslate2 is a C++ library designed to run Transformer models efficiently. It supports various model types, including language models, speech-to-text, and machine translation. This component provides a server CLI and a class-based generic API with callback functions to use CTranslate2 from 4D.

Qwen 3.5 in GGUF

Local inference engine

Datasets to train an LLM to generate better 4D code

Local inference engine

Local inference engine

MarianMT in CT2

Bonsai 8B in GGUF

Local inference engine

AI Gateway proxy