Repository Index

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

• fine-tuning
• llama
• llms
• gemma

Inference code for Llama models

Grok open release

Run frontier AI locally.

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

TranslatedChatGLM-6B: An Open Bilingual Dialogue Language Model

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

• apple-silicon
• inference-server
• llm
• macos

Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported

Run LLMs with MLX

• llms
• mlx

A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.

Run many AI agents at once on your Mac, up to 3x faster.

• agents
• apple-silicon
• artificial-intelligence
• inference-acceleration

Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts

• gguf
• humanizer
• llama-cpp
• llm

A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.

• gated-deltanet
• interpretability
• llm
• qwen

Our lightning-fast inference engine.

On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.