Views
No views yet
GGUF version of our Opus 4.6 reasoning model. Ollama ✅ LM Studio ✅ llama.cpp ✅ Reasoning baked in — no adapter needed.
gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit — Gemma 4 E4B with Opus 4.6 reasoning and Claude Code LoRA fused directly into the weights.<think> reasoning baked in.Looking for the Apple Silicon MLX version? → MLX 4-bit model (optimized for Metal GPU)
| Quantization | Size | Use case |
|---|---|---|
Q4_K_M | 2.7 GB | Recommended — best balance of quality and speed |
Q5_K_M | 3.1 GB | Higher quality, slightly more RAM |
Q8_0 | 4.5 GB | Near-lossless, needs more RAM |
F16 | 8.3 GB | Full precision GGUF |
Sizes will be updated once conversion is complete.
ollama run hf.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUFModelfile:FROM hf.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF
SYSTEM "You are a helpful assistant with tool-use capabilities. Think through problems step by step using <think> tags."
PARAMETER temperature 0.7
PARAMETER num_ctx 81921ollama create ravenx-gemma4 -f Modelfile
2ollama run ravenx-gemma41curl http://localhost:11434/v1/chat/completions \
2 -H "Content-Type: application/json" \
3 -d '{
4 "model": "hf.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF",
5 "messages": [{"role": "user", "content": "Explain why RSA encryption is hard to break."}]
6 }'deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF1llama-cli \
2 -hf deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF \
3 -p "Explain why RSA encryption is hard to break." \
4 -n 10241llama-server \
2 -hf deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF \
3 --port 8080
4
5# Use with any OpenAI client
6curl http://localhost:8080/v1/chat/completions \
7 -H "Content-Type: application/json" \
8 -d '{
9 "model": "gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF",
10 "messages": [{"role": "user", "content": "Hello!"}]
11 }'| Base Gemma 4 E4B | This model | |
|---|---|---|
<think> tag reasoning | ❌ | ✅ baked in |
| Claude-style structured answers | ❌ | ✅ |
| Tool-use patterns | ❌ | ✅ |
| Requires adapter | — | ❌ no adapter needed |
| Vision support | ✅ | ✅ |
| Ollama / LM Studio / llama.cpp | ✅ | ✅ |
| Space | What to try |
|---|---|
| 🔥 Agentic Tool Calling Demo | Live agentic loop — tool calling, <think> reasoning, calculator, web search |
| 🐳 OpenClaw Sandbox Demo | OpenClaw-style orchestration, Docker runtime, sandbox/approval modes |
| Layer | Role |
|---|---|
| Gemma 4 E4B Opus Reasoning + Claude Code | Reasoning + tool-use baked into 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 |
| Source | Examples |
|---|---|
| Crownelius/Opus-4.6-Reasoning-2100x-formatted | 2,054 |
| Claude Code tool-use patterns | 140 files |
| Total | 2,163 |
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-7llama.cpp/convert_hf_to_gguf.pyllama-quantize| Model | Format | Size | Notes |
|---|---|---|---|
| MLX 4-bit (source) | MLX | ~10.5 GB | Apple Silicon optimized, Metal GPU |
| This model (GGUF) | GGUF | varies | Ollama, LM Studio, llama.cpp |
| Base model (4-bit) | MLX | 4.86 GB | Base model (use with adapter) |
| LoRA adapter only | Safetensors | 658 MB | Adapter-only |
| 2B abliterated | MLX | 3.34 GB | 2B abliterated |
| 21B MoE REAP | MLX | 12 GB | 21B MoE REAP |