---
library_name: gguf
license: gemma
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
pipeline_tag: text-generation
tags:
- gguf
- gemma4
- quantized
- reasoning
- chain-of-thought
- sol
- fable
- opus
- sft
- fused
- ravenx
- tool-calling
- function-calling
- agentic
- coding
- ollama
- llama-cpp
- lm-studio
base_model: deadbydawn101/gemma-4-E4B-mlx-4bit
base_model_relation: finetune
language:
- en
datasets:
- greghavens/gpt-5.6-sol-coding-and-debugging-traces
- Crownelius/Complete-FABLE.5-traces-2M
- Crownelius/Opus-4.6-Reasoning-2100x-formatted
---
# Gemma 4 E4B v2 — Sol + FABLE.5 + Opus Reasoning + Claude Code | 22K Examples | No Adapter Needed | Tool Calling ✅ | OpenHarness ✅ | OpenClaw ✅ | Hermes Agent ✅ | Reasoning Baked In GGUF
> **Thank you for 140,000+ downloads on v1. We were the first to train Gemma 4 at the weights. We will continue to innovate and simply do what others can't.**
### Built by [RavenX AI Labs](https://github.com/DeadByDawn101) — San Jose, CA
[]()
[](https://ai.google.dev/gemma/docs/gemma_4_license)
[](https://huggingface.co/deadbydawn101/gemma-4-E4B-Agentic-Sol-Fable-Reasoning-GeminiCLI-mlx-4bit)
---
## GGUF Downloads
| Quant | Size | Use Case |
|-------|------|----------|
| **Q4_K_M** | 5.07 GB | Best balance of quality and size — recommended |
| **F16** | 15.0 GB | Full precision, maximum quality |
### For the MLX version (Apple Silicon native), see:
👉 **[gemma-4-E4B-Agentic-Sol-Fable-Reasoning-GeminiCLI-mlx-4bit](https://huggingface.co/deadbydawn101/gemma-4-E4B-Agentic-Sol-Fable-Reasoning-GeminiCLI-mlx-4bit)**
---
## Quickstart
### Ollama
```bash
ollama run hf.co/deadbydawn101/gemma-4-E4B-Agentic-Sol-Fable-Reasoning-GeminiCLI-GGUF
```
### llama.cpp
```bash
llama-cli -m gemma-4-E4B-v2-Sol-Fable-Q4_K_M.gguf \
-p "Write a Python function that implements binary search with error handling." \
-n 2048
```
### LM Studio
Download the Q4_K_M GGUF and load directly in LM Studio.
---
## What's New in v2
This is the 10x update to the model that started it all. 22,389 training examples, up from 2,163.
| | v1 (April 2026) | v2 (July 2026) |
|---|---|---|
| **Training examples** | 2,163 | **22,389 (10x)** |
| **Data sources** | Opus reasoning | Sol + FABLE.5 + Opus |
| **Coding traces** | 0 | **17,939 (xhigh reasoning, tool use)** |
| **Thinking traces** | 0 | **4,450 (with `` blocks)** |
| **Final training loss** | — | **1.8984** |
| **Adapter needed?** | No | **No** |
### Data Sources
| Dataset | Examples | What It Teaches |
|---------|----------|----------------|
| [GPT-5.6 Sol Coding Traces](https://huggingface.co/datasets/greghavens/gpt-5.6-sol-coding-and-debugging-traces) | 17,939 | Production coding, debugging, tool use, acceptance-tested solutions |
| [Complete FABLE.5 Traces](https://huggingface.co/datasets/Crownelius/Complete-FABLE.5-traces-2M) | 4,450 | Deep reasoning with `` blocks, context→completion |
| [Opus 4.6 Reasoning](https://huggingface.co/datasets/Crownelius/Opus-4.6-Reasoning-2100x-formatted) | 2,163 | Claude-style structured reasoning (from v1) |
---
## Gym Benchmarks — 7B Model, Local Apple Silicon
Evaluated on 6 hard tasks across security, coding, and reasoning. All responses generated locally on M4 Max 128GB at 15.5 tokens/sec average.
| Task | Category | Tokens | Speed | Result |
|------|----------|--------|-------|--------|
| **RATH Security Report** | Security | 1,378 | 25.1 t/s | Full CVSS + CWE + MITRE ATT&CK report |
| **Privilege Escalation** | Security | 385 | 24.1 t/s | Correctly refused unauthorized exploitation |
| **Thread-Safe LRU+TTL Cache** | Coding | 4,270 | 15.3 t/s | Production Python with full test suite |
| **CSV Data Pipeline** | Agentic Coding | 8,192 | 14.9 t/s | Hit max tokens — wanted to write MORE |
| **Combinatorics Problem** | Math Reasoning | 3,072 | 14.9 t/s | Formal set theory with LaTeX notation |
| **Distributed Rate Limiter** | System Design | 3,676 | 15.0 t/s | Complete Redis-backed implementation |
**Total: 20,973 tokens generated in 22 minutes. 5/6 production quality, 1/6 correct safety refusal.**
---
## The Story
On April 2, 2026, Google released Gemma 4. Its `gemma4` architecture wasn't supported by any training framework.
**On April 9, we shipped the first working fine-tune.** Seven days. We built [custom Gemma 4 support](https://github.com/DeadByDawn101/unsloth-mlx) into our training framework and shipped before anyone else.
Unsloth published their Gemma 4 training guide on July 18 — three months later.
140,000+ people downloaded v1. Zero community issues. v2 is our thank you — 10x the training data.
## All Formats
| Format | Link |
|--------|------|
| 🆕 **GGUF (this repo)** | You're here |
| 🆕 **[MLX 4-bit (v2)](https://huggingface.co/deadbydawn101/gemma-4-E4B-Agentic-Sol-Fable-Reasoning-GeminiCLI-mlx-4bit)** | Apple Silicon native |
| **[v2 LoRA adapters](https://huggingface.co/deadbydawn101/gemma-4-E4B-v2-Sol-FABLE5-lora)** | Standalone adapters |
| **[v1 MLX (Opus only)](https://huggingface.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit)** | Original 140K download model |
| **[v1 GGUF (Opus only)](https://huggingface.co/deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-GGUF)** | Original GGUF |
## The RavenX Gemma 4 Stack
| Repo | What |
|------|------|
| [unsloth-mlx](https://github.com/DeadByDawn101/unsloth-mlx) | Training framework — we added Gemma 4 support |
| [mlx-gemma4](https://github.com/DeadByDawn101/mlx-gemma4) | Custom model implementation + converter |
| [ravenx-mtp-drafter](https://github.com/DeadByDawn101/ravenx-mtp-drafter) | Reverse-engineered Google's hidden MTP heads |
| [ravenx-training-gym](https://github.com/DeadByDawn101/ravenx-training-gym) | Harbor-native security benchmark |
## About RavenX AI Labs
Security AI infrastructure company. San Jose, CA. 200K+ HF downloads. 26+ shipped models. 2 USPTO patents filed.
- **USPTO #64/087,357** — Soul Infusion (identity-framed training)
- **USPTO #64/104,760** — Sovereignty Chain (cryptographic model protection)
GitHub: [@DeadByDawn101](https://github.com/DeadByDawn101) | X: [@RavenXllm](https://x.com/RavenXllm)
---
*"We trained Gemma 4 in April. Unsloth published their guide in July. We simply do what others can't."*
*— RavenX AI Labs LLC, since June 2026*