MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

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

The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Initial geniex-qairt-plugin

Open Machine Learning Compiler Framework

LLM inference in C/C++

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

A repo for llm on ncnn

LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

Development repository for the Triton language and compiler

AI Edge Quantizer: flexible post training quantization for LiteRT models.

Support PyTorch model conversion with LiteRT.

Orchestrate coding agents remotely from your phone, desktop and CLI

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents, GUI Agent…

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

A safetensors extension to efficiently store sparse quantized tensors on disk

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM