--- library_name: mlx license: gemma license_link: https://ai.google.dev/gemma/docs/gemma_4_license pipeline_tag: text-generation tags: - mlx - safetensors - gemma4 - 4-bit - quantized - apple-silicon - multimodal - vision - reasoning - chain-of-thought - opus - claude-code - sft - fused - turboquant - kv-cache-compression - long-context - ravenx - tool-calling - function-calling base_model: deadbydawn101/gemma-4-E4B-mlx-4bit base_model_relation: finetune language: - en datasets: - Crownelius/Opus-4.6-Reasoning-2100x-formatted ---
# Gemma 4 E4B — Opus Reasoning + Claude Code | Tool Calling ✅ | OpenHarness ✅ | OpenClaw ✅ | Hermes Agent ✅ | Reasoning Baked In > **Opus 4.6 reasoning + Claude Code fused into weights. Native tool calling. OpenHarness agent harness. OpenClaw orchestration. Hermes terminal-agent skill. `` reasoning baked in — no adapter needed. 10.5 GB.** ### Reasoning baked in. No adapter needed. Built by [RavenX AI](https://github.com/DeadByDawn101) [![TurboQuant](https://img.shields.io/badge/TurboQuant--MLX-4.6x_KV_compression-blueviolet)](https://github.com/DeadByDawn101/turboquant-mlx) [![Gemini CLI](https://img.shields.io/badge/Gemini_CLI-MCP_compatible-blue)](https://github.com/DeadByDawn101/gemini-cli) [![License](https://img.shields.io/badge/license-Gemma-green)](https://ai.google.dev/gemma/docs/gemma_4_license)
--- **Gemma 4 E4B with Opus Reasoning + Claude Code LoRA fused directly into the weights** — no adapter needed, no extra memory, just load and run with Claude-style `` reasoning baked in. > **~10.5 GB. 131K context. Text + vision. Drop-in reasoning upgrade.** This is [`gemma-4-E4B-mlx-4bit`](https://huggingface.co/deadbydawn101/gemma-4-E4B-mlx-4bit) with the [Opus Reasoning + Claude Code LoRA](https://huggingface.co/deadbydawn101/gemma-4-E4B-opus-reasoning-claude-code-lora) merged directly into the base weights using `mlx` weight arithmetic. --- ## What's different from the base model | | Base model | This model | |--|:--:|:--:| | `` tag reasoning | ❌ | ✅ baked in | | Claude-style structured answers | ❌ | ✅ | | Tool-use patterns | ❌ | ✅ | | Requires adapter | — | ❌ no adapter needed | | File size | 4.86 GB (4-bit) | ~10.5 GB (bfloat16 merged) | | Vision support | ✅ | ✅ | --- ## 🧪 Live Demos — Try It Now
| Space | What to try | |---|---| | 🔥 [**Agentic Tool Calling Demo**](https://huggingface.co/spaces/deadbydawn101/gemma4-agentic-tool-calling-demo) | Live agentic loop — tool calling, `` reasoning, calculator, web search | | 🐳 [**OpenClaw Sandbox Demo**](https://huggingface.co/spaces/deadbydawn101/openclaw-agent-sandbox-demo) | OpenClaw-style orchestration, Docker runtime, sandbox/approval modes |
## Quickstart ```bash pip install mlx-lm mlx-vlm ``` ```python from mlx_lm import load, generate # No adapter_path needed — reasoning is in the weights model, tokenizer = load("deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit") messages = [{"role": "user", "content": "Explain why RSA encryption is hard to break."}] prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) response = generate(model, tokenizer, prompt=prompt, max_tokens=1024, verbose=True) # → Will produce ... followed by structured answer ``` ### CLI ```bash mlx_lm.generate \ --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit \ --prompt "Debug this Python code: def fib(n): return fib(n-1) + fib(n-2)" \ --max-tokens 1024 ``` --- ## 🧩 OpenHarness + OpenClaw + Hermes Agent This model is built to sit inside a **real agent stack**, not just a chat box. We support: - **[OpenHarness](https://github.com/HKUDS/OpenHarness)** for agent harness/runtime, skills, hooks, tool loops, and multi-agent flows - **OpenClaw** for orchestration, sessions, reminders, and cross-agent routing - **Hermes agent skill** for terminal-native coding posture, short planning, aggressive tool use, and repo-aware execution ### Why this combo matters | Layer | Role | |---|---| | **Gemma 4 E4B Opus Reasoning + Claude Code** | reasoning + tool-use behavior baked into the weights | | **Gemini CLI** | coding agent + tool orchestration | | **OpenHarness** | harness runtime, tool loop, swarm, hooks, memory | | **OpenClaw** | orchestration, sessions, skills, messaging | | **Hermes skill** | agent behavior for concise, terminal-first execution | ### OpenHarness quickstart ```bash pip install openharness mlx_lm.server \ --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit \ --port 8080 oh --model http://localhost:8080/v1 \ --skill hermes-agent \ -p "Review this repo, find bugs, patch them, and summarize the result" ``` ### OpenClaw skill stack Inside OpenClaw, pair this model with: - `openharness` skill — run/configure `oh` - `hermes-agent` skill — shape coding-agent behavior That gives you a fully local Apple Silicon agent lane with: - baked-in reasoning - native tool calling - Gemini CLI integration - OpenHarness runtime support - OpenClaw orchestration ## 💻 Gemini CLI — Coding Agent + Tool Orchestration We use **[RavenX AI's Gemini CLI fork](https://github.com/DeadByDawn101/gemini-cli)** as the coding agent and tool orchestration layer on top of these models. This is what makes the tool-calling capability real in production. Gemini CLI gives you a full agentic loop in the terminal — Google Search grounding, file read/write, shell execution, web fetching, and MCP server support — all wired to a 1M token context window. ```bash # Install npm install -g @google/gemini-cli # Run as a coding agent against this model (via local mlx_lm server) mlx_lm.server --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit --port 8080 & gemini --baseUrl http://localhost:8080 # Or use directly against Gemini API (free tier: 60 req/min) gemini ``` ### What Gemini CLI + these models unlock together | Capability | How | |---|---| | **Code generation** | Gemini CLI reads your codebase, model reasons with `` tags | | **Tool calling** | Native `<\|tool>` tokens → Gemini CLI executes shell/file/web tools | | **Long context** | 1M ctx in CLI + TurboQuant 4.6x KV compression = very long sessions | | **MCP servers** | Connect any MCP server — databases, APIs, custom tools | | **Search grounding** | Google Search built in — model gets live data | ```bash # Real example: code review with tool calling enabled gemini --baseUrl http://localhost:8080 \ "Review all Python files in ./src, find potential bugs, and suggest fixes" # Gemini CLI will: read files → call tools → model reasons → produce structured output ``` → [DeadByDawn101/gemini-cli on GitHub](https://github.com/DeadByDawn101/gemini-cli) — Apache 2.0, free tier, MCP-compatible ## ⚡ TurboQuant-MLX — 4.6x KV Cache Compression Pair with [TurboQuant-MLX](https://github.com/DeadByDawn101/turboquant-mlx) to compress the KV cache and run 4.6x longer reasoning chains at the same memory: ```python from turboquant_mlx.mlx_kvcache import TurboQuantKVCache import mlx_lm.models.cache as cache_module cache_module.make_prompt_cache = lambda model, **kw: [ TurboQuantKVCache() for _ in range(len(model.layers)) ] from mlx_lm import load, generate model, tokenizer = load("deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit") # Long reasoning chains now fit in the same RAM budget ``` → [TurboQuant-MLX on GitHub](https://github.com/DeadByDawn101/turboquant-mlx) · [v2.0 Release](https://github.com/DeadByDawn101/turboquant-mlx/releases/tag/v2.0.0) --- ## How it was made ### Training data | Source | Examples | |--------|--------:| | Crownelius/Opus-4.6-Reasoning-2100x-formatted | 2,054 | | Claude Code tool-use patterns | 140 files | | **Total** | **2,163** | ### Training ``` Base: deadbydawn101/gemma-4-E4B-mlx-4bit Method: SFT completions-only (mlx_vlm.lora) Rank: 8 · Alpha: 16 · LR: 1e-5 · Iters: 1,000 Hardware: Apple M4 Max 128GB · Peak mem: 7.876 GB Final loss: ~3.5e-7 ``` ### Fusion All **378 LoRA pairs** merged via weight arithmetic: ``` W_merged = dequantize(W_base) + (A @ B).T × (alpha / rank) ``` Result dequantized to bfloat16 and saved as 3-shard safetensors. --- ## 🦙 Ollama / LM Studio / llama.cpp > **This is an MLX model optimized for Apple Silicon.** For Ollama, LM Studio, or llama.cpp, use the GGUF version: > > 👉 **[gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF](https://huggingface.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF)** > > Available in Q4_K_M (2.7 GB), Q5_K_M (3.1 GB), Q8_0 (4.5 GB), and F16 (8.3 GB). > > ```bash > ollama run hf.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF > ``` ### Run with mlx_lm server (native, faster on Apple Silicon) ```bash mlx_lm.server --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit --port 8080 curl http://localhost:8080/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model": "deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit", "messages": [{"role": "user", "content": "Hello!"}]}' ``` ## Related models | Model | Size | Notes | |-------|------|-------| | [gemma-4-E4B-mlx-4bit](https://huggingface.co/deadbydawn101/gemma-4-E4B-mlx-4bit) | 4.86 GB | Base model (4-bit, use with adapter) | | **gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit** | ~10.5 GB | **This model** — fused, no adapter needed | | [**GGUF version**](https://huggingface.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF) | 2.7-8.3 GB | Ollama, LM Studio, llama.cpp | | [gemma-4-E4B-opus-reasoning-claude-code-lora](https://huggingface.co/deadbydawn101/gemma-4-E4B-opus-reasoning-claude-code-lora) | 658 MB | Adapter-only | | [gemma-4-E2B-Heretic-Uncensored-mlx-4bit](https://huggingface.co/deadbydawn101/gemma-4-E2B-Heretic-Uncensored-mlx-4bit) | 3.34 GB | 2B abliterated | | [gemma-4-21b-REAP-Tool-Calling-mlx-4bit](https://huggingface.co/deadbydawn101/gemma-4-21b-REAP-Tool-Calling-mlx-4bit) | 12 GB | 21B MoE REAP | --- ## License [Gemma Terms of Use](https://ai.google.dev/gemma/docs/gemma_4_license) ---
Built with 🖤 by RavenX AI · TurboQuant-MLX · Gemini CLI
## TriAttention KV Compression > **[2026-04-09] Our MLX port was merged into [TriAttention](https://github.com/WeianMao/triattention) (MIT + NVIDIA) — PR #1 by [@DeadByDawn101](https://github.com/DeadByDawn101) (RavenX AI).** Apply **10.7x KV memory reduction** and **2.5x throughput** on top of this model's built-in 4-bit TurboQuant quantization for ~50x combined compression vs full fp16: ```python from mlx_lm import load from triattention.mlx import apply_triattention_mlx model, tokenizer = load("deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit") apply_triattention_mlx(model, kv_budget=2048) ``` ## RavenX Inference Harness One-command inference, benchmarking, and local OpenAI-compatible server: ```bash git clone https://github.com/DeadByDawn101/ravenx-inference-harness cd ravenx-inference-harness # Inference python run.py --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit --prompt "Your prompt" # TriAttention compressed python run.py --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit --triattention --kv-budget 2048 # Local OpenAI-compatible server (works with OpenClaw) python serve.py --model deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit --triattention ```