A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.1, Claude, Grok, DeepSeek, OpenRouter, Kimi 2.5, GLM 5, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.5

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.

AI That Builds Screens, Not Just Text

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

Local AI Assistant on your phone

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

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.

Local AI desktop app — chat, agent mode, image gen, video gen. Supports Ollama, Gemma 4, Llama, Qwen, OpenAI, Anthropic. Single .exe, no Docker.

A privacy-first Android chat app that runs large language models entirely on-device. No internet, no cloud, no tracking. Built with Kotlin, Jetpack Compose, and llama.cpp with optimized ARM NEON/SVE inference.

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

Fast Gemma 4 inference in pure Java

Standalone Gemma 4 PyTorch Model using Claude Code

Dockerized inference server and benchmarks for quantized Gemma 4 family on the NVIDIA DGX Spark (GB10). Features ARM64 CUDA 13 builds using llama.cpp.

Hooman is a Bun-powered local AI agent CLI built with TypeScript, Strands Agents SDK, and Ink.

Run Google's Gemma 4 models entirely on-device, embedded in a Node.js process. Text, image, and audio in — text out. No API keys, no cloud, no network required after the initial model download.

Autonomous AI-powered job search engine. Scans 139 companies, scores jobs 1-10, tailors CVs, preps interviews. Runs while you sleep. $0 AI cost.

A Transformer(gemma3N E4B LLM & gemma 4 E4B)accelerator based on a 2D Systolic Array, bitShift-Adder, SFU-core, architecture and dynamic multi channel memory management optimization techniques designed by SystemVerilog for edge devices. Target board: KV260(FPGA), Tool: Xilinx Vivado

NVFP4 AWQ Full quantization of SuperGemma4-26B-Abliterated-Multimodal for Blackwell GPUs — pre-built vLLM container + patches included

A C# inference engine for running large language models (LLMs) locally using GGUF model files. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access.