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

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

Standalone Gemma 4 PyTorch Model using Claude Code

Validated Gemma4 GPTQ on Ampere (RTX 3090/3060) — Marlin JIT nvcc compatibility fixes included

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

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

Local AI that indexes, understands, and tells the story of everything on your machine. Powered by Gemma 4 via Ollama.

Standalone Gemma4 PyTorch Model using Codex (GPT-5.4 xhigh)

NovaLIS is a governed local AI system that separates intelligence from execution.

A pipeline for preparing data from personal audio call recordings and then fine-tuning LLMs using LoRA.

把单个 AI 助手升级为可扩展的多专家协作运行时， 带工业级记忆检索、会话管理和完整的开发者可观测性。

100-question benchmark comparing proprietary (2025) and open-source (2026) LLMs.

CLI pipeline that extracts anime titles, GitHub URLs, and recipes from Instagram screenshots into structured JSON, CSV, and Notion databases

GAFA takes any text or image, extracts verifiable claims, and cross-references them against the Google Fact Check API and user-provided documents to deliver evidence-based verdicts in real time.

A local-first framework for building customizable AI powered voice assistants on Apple Silicon Macs with local speech, knowledge & tools.

Local, AMD-supported autonomous browser agent. Privacy-first task automation via LM Studio and Gemma 4.

SAM3-Gemma4-CUDA is an experimental computer vision and multimodal reasoning application that combines Facebook's Segment Anything Model 3 (SAM3) with Gemma 4 multimodal model. This suite offers a comprehensive interactive web interface for high-precision image object detection, video segmentation, and interactive click-based tracking.

Local AI Assistant, Using Gemma4/Ollama

Parlor Vision es un asistente de IA conversacional que escucha, ve y responde — todo ejecutándose 100% en tu máquina. Sin nube, sin APIs externas. Optimizado para español, con soporte de cámara y pantalla compartida.

Fully local LLM Wiki — Karpathy's knowledge base pattern with Gemma 4, Unsloth Dynamic, and TurboQuant KV cache. Zero dependencies. Runs on a MacBook.