Gemma 4 Agent Skills
Autonomous AI Agent Skill for Google AI Edge Gallery - self-evolving, 100% offline
The first native Swift inference engine for Gemma 4 on Apple Silicon / iOS
Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via MLX.
Run Gemma 4 locally with Gemma-4 Omni-Desktop. A free, offline AI agent optimized for RTX 30xx & 8GB Macs. Features native vision, voice & OpenClaw support.
Domain-specialized Gemma 2 27B + Gemma 4 31B for SEC filings — fine-tuned on TPU v6e-8 with PyTorch/XLA FSDPv2, plus a Vertex AI Vector Search RAG demo (69 tickers × 381 filings). Same LoRA recipe, +3.5% / +5.8% BERTScore F1.
A privacy-first, local-first AI workstation for 1-1 practitioners that scales your professional framework without losing your unique voice.
Claude Code Skills for building offline-capable AI features with Gemma 4 on-device LLM inference in Flutter apps. Includes scaffold templates, function calling guides, and reusable AI skill architecture.
Distributed systems for automated proposal generation. Orchestrates LLM agents for requirement extraction, semantic inventory matching, and competitive pricing analysis
Gemma 4 on a 24GB MacBook: measured recipes, runtimes, and fallback paths.
Offline subtitle translator with 2026 LLMs (Gemma 4, Qwen 3.5, Hunyuan-MT, Llama 4 Scout) via Ollama. Web UI + CLI, 17 languages, video subtitle extraction, persistent Translation Memory, LLM-as-judge quality estimation, genre-aware prompts. No API keys, no cloud.
Run Google's Gemma 4 entirely in your browser via WebGPU. Multimodal chat, E2B vs E4B arena, ONNX conversion toolkit.
Run Google Gemma 4 AI locally on your Mac. No internet, no subscriptions, no data leaves your device. Free forever.
Download Gemma 4 Lightweight Installer. Run Gemma 4 26B MoE & 31B Dense locally in one click. 100% offline AI, zero-setup, powered by highly optimized llama.cpp
Benchmark Gemma 4 E2B on Apple Silicon: MLX (mlx-lm) vs GGUF (llama-server), with TTFT, tokens/sec, and memory.
HarmonyOS NEXT native Gemma 4 MNN on-device LLM chat demo
Drop-in KV cache compression for MLX on Apple Silicon. Brings PolarQuant (Google, ICLR 2026) to mlx-lm with first-class Gemma 4 support: MatFormer, dual head_dim, hybrid sliding/global attention, cross-layer KV sharing. 3-bit → 4.8× smaller cache, 0.995 logit cosine @ 4-bit.
Local multi-agent execution with middleware-level deduplication.
Add a description, image, and links to the gemma-4 topic page so that developers can more easily learn about it.
To associate your repository with the gemma-4 topic, visit your repo's landing page and select "manage topics."