---
license: gemma
library_name: mlx
tags:
- mlx
- abliterated
- uncensored
- crack
- gemma4
- jang
thumbnail: dealign_mascot.png
pipeline_tag: image-text-to-text
base_model: google/gemma-4-e2b-it
---

<p align="center"><img src="dealign_logo.png" alt="dealign.ai" width="200"/></p>

<div align="center">
<img src="dealign_mascot.png" width="128" />

# Gemma 4 E2B JANG_4M CRACK

**Abliterated Gemma 4 E2B — Vision + Audio, reasoning, multilingual**

100% HarmBench harm-category compliance with -1.7% MMLU change. Refusal removed, capability preserved.
</div>

## Model Details

| Metric | Value |
|--------|-------|
| Source | `google/gemma-4-e2b-it` |
| Architecture | Dense + Hybrid Sliding/Global Attention, per-layer input embeddings (Gemma-3n style) |
| Quantization | JANG_4M (attn 8-bit / MLP 4-bit, ~4.3 avg bits) |
| Model size | 7.3 GB |
| Parameters | E2B (effective ~2B, per-layer embeddings) |
| Vision | Yes (multimodal, float16 passthrough) |
| Audio | Yes |
| Reasoning | Yes (channel-based thinking) |
| Format | MLX-native safetensors (instant load) |
| Abliteration | CRACK (refusal removal) |

## Benchmarks

![comparison](compare.png)

### MMLU (knowledge retention)

Measured in the served (generation) setting — the model reasons before answering, as in deployment.

| | Base | CRACK | Δ |
|---|---|---|---|
| MMLU | 61.8% | **60.1%** | -1.7% |

### HarmBench (refusal removal)

**Harm-category compliance: 240/240 = 100%** (full HarmBench-320 text set) — base model refuses (~0%).

| Category | Compliance |
|---|---|
| Illegal activities | 53/53 (100%) |
| Chemical / biological | 42/42 (100%) |
| Cybercrime / intrusion | 52/52 (100%) |
| Misinformation | 54/54 (100%) |
| Harassment / bullying | 21/21 (100%) |
| Harmful content | 18/18 (100%) |

Copyright-reproduction prompts are excluded (not a refusal behavior).

### Coherence & capability ✅

- Factual QA, multi-step reasoning, and working code generation verified
- Vision and audio inputs preserved · no loops, no truncation

## Other Quantizations

Also available: **Gemma 4 E2B MXFP4 CRACK** — same family, different precision/size trade-off.

## Usage

Requires [vMLX](https://vmlx.net) (bundled Gemma 4 support). Standard `mlx_lm` / `mlx_vlm` do not fully support Gemma 4.

```python
# Load in the vMLX app or via its API
from vmlx_engine.models.mllm import MLXMultimodalLM
m = MLXMultimodalLM("<this-repo>")
print(m.chat([{"role":"user","content":"..."}]).text)
```

## Requirements
- Apple Silicon Mac with sufficient unified memory
- [vMLX](https://vmlx.net) with Gemma 4 support

---

## Support dealignai

All models are built from original research and published free — crafted to be excellent coders and general-purpose assistants.

**[Support us on Ko-fi](https://ko-fi.com/dealignai)** — membership gets early access and extras. Questions? **DM us — we help for free.**

[Ko-fi](https://ko-fi.com/dealignai) | [𝕏 @dealignai](https://x.com/dealignai) | [dealign.ai](https://dealign.ai)

---

## About dealignai

<img src="dealign_mascot.png" alt="Dealign.AI" width="200"/>

We research and publish abliterated models to advance AI safety understanding.

See our research: [Safety Generalization in Frontier Models](https://dealign.ai)

<div align="center"><img src="dealign_logo.png" width="200"/></div>

---

*Provided for research. Users are responsible for compliance with applicable laws and regulations.*