Skip to content
@LMGNU

LMGNU

local-first LLM systems. Training & Inference
README.md

LMGNU

lmgnu

LMGNU develops frameworks for local-first Large Language Model (LLM) systems. We design practical, optimized architectures that enable both training and inference directly on local infrastructure - prioritizing data privacy, low latency, and resource efficiency.

Repositories

Repository Description
llm.cpp Core inference engine optimized for localized, lightweight training.
LLM-Engine python based resource management, pipeline orchestration.
prism Tooling and interfaces optimized for local data processing.
nanollm Compact LLM implementations simple and local training.

Pinned Loading

  1. llm.cpp llm.cpp Public

    LLM training in C++ & Python.

    C++ 3 1

  2. LLM-Engine LLM-Engine Public

    Character-level transformer

    Python 6 3

  3. prism prism Public

    Character-level language model training pipeline in C++.

    C++ 2

  4. LMGNU LMGNU Public

    automatic differentiation engine and neural network library

    Python 2 1

Repositories

Showing 5 of 5 repositories

Top languages

Loading…

Most used topics

Loading…