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

A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.5, Claude, DeepSeek V4, Grok, OpenRouter, Kimi 2.6, GLM 5, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.7

Steno is the AI powered intelligence layer for all your confidential workflows. On Windows & MacOS. Perfect for government, defence, legal and CXOs.

OpenClaw alternative in your pocket

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

Uncensored local AI desktop app: chat, agent mode, image & video generation. Run abliterated/uncensored LLMs + ComfyUI fully offline with your own provider. Single .exe, no Docker.

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Local AI Assistant on your phone

An open-source Cotypist with macOS system wide AI autocomplete

Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

🤖FFPA: Extends FlashAttention-2 via Split-D for large headdims, 1.5x~3×↑🎉 vs SDPA, up to 430T🎉 on H200.

llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% throughput).

Community model zoo + knowledge base for Apple Core AI (iOS/macOS 27): Qwen3.5 & Gemma 4 converted end-to-end, verified on-device (iPhone 17 Pro GPU/ANE), conversion gotchas, custom Metal kernels, Swift runner

This is end to end course on AI Agents and Agentic AI with 15+ AI Agent Projects with real time use cases and industry expertise.

Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection.

Agentic ✧ Gemma Inference for Android System Intelligence

A native .NET LLM inference engine for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/Linux with full GPU capability

Automated image & video captioning using Qwen-VL, Gemma4 and SAM3.

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3-Next, GLM-5.1, Deepseek-V4, MiniMax-2.7, ...) and 200+ multimodal large models (Qwen3.5, Qwen3-Omni, Gemma4, ...).