deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit

Update README.md

Thank you for 140K downloads — v2 is here (10x training data, Sol + FABLE.5)

update: replace Ollama section with GGUF cross-link, add GGUF to related models

fix: remove ollama tag (MLX model, not GGUF compatible)

docs: TriAttention merge credit + inference harness

Add Live Demos section linking both HF Spaces

Fix: add format=pt metadata to model-00003-of-00003.safetensors — fixes LM Studio 'Unsupported safetensors format: null'

Fix: add format=pt metadata to model-00002-of-00003.safetensors — fixes LM Studio 'Unsupported safetensors format: null'

Fix: add format=pt metadata to model-00001-of-00003.safetensors — fixes LM Studio 'Unsupported safetensors format: null'

Update cross-links: gemma-4-E4B-Opus-Reasoning-Claude-Code-mlx-4bit → gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit

Title: add OpenHarness, OpenClaw, Hermes Agent to H1 so stack is visible without clicking

Add OpenHarness, OpenClaw, and Hermes agent support section

Add Gemini CLI coding agent + tool orchestration section with real usage examples

Crown-worthy titles: clear name + tool calling + size + platform in H1, punchy subtitle, cross-links updated

Add 'Tool Calling ✅' to model title and subtitle

Add native tool calling docs, Ollama Modelfile, OpenAI-compatible endpoint examples

Add model card: fused Opus reasoning baked into weights, training details, TurboQuant, Gemini CLI

Fused: gemma-4-E4B-mlx-4bit + Opus Reasoning + Claude Code LoRA (baked weights)

initial commit