CoolFace
Modelpublic

Ishowbackup/MiniMax-M2.5-UNCENSORED-JANG_2L

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face
0likes266downloads
Model Card
Important: This model uses the JANG quantization format — the GGUF equivalent for MLX on Apple Silicon. Currently only supported by [MLX Studio](https://mlx.studio) and the jang-tools Python package.

<p align="center"> <a href="https://mlx.studio"><img src="https://raw.githubusercontent.com/jjang-ai/jangq/main/assets/mlx-studio-light.png" alt="MLX Studio" width="500"></a> </p>

<p align="center"> <a href="https://mlx.studio"><img src="https://mlx.studio/assets/screenshots/mlx-studio-featured.png?v=1" alt="MLX Studio App" width="600"></a> </p>

<h4 align="center"><a href="https://mlx.studio">MLX Studio</a> — the only app that natively supports JANG models</h4>

<div align="center">

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

MiniMax M2.5 — JANG_2L + CRACK

JANG mixed-precision · CRACK abliterated · No guardrails · 63 GB

<a href="https://ko-fi.com/jangq"><img src="https://img.shields.io/badge/Ko--fi-Support_Development-FF5E5B?logo=ko-fi&logoColor=white&style=for-the-badge" alt="Ko-fi"></a>

</div>

What Is This?

This is MiniMax M2.5 — a 230B parameter Mixture-of-Experts model with 256 experts (8 active per token), all standard attention (no SSM), and trained with chain-of-thought reasoning.

It has been:

  1. 1.JANG quantized — JANG_2L profile (8-bit attention, 6-bit embeddings, 2-bit experts) — 63 GB
  2. 2.CRACK abliterated — permanent weight-level removal of safety refusal
ArchitectureMiniMax M2.5 MoE — 230B total, ~10B active, 256 experts
QuantizationJANG_2L (8/6/2-bit mixed) — 63 GB
AbliterationCRACK — novel weight surgery
MMLU-20084.7% (base: 74.5%, +10.2% improvement)
HarmBench98.1% (314/320)
Compliance7/8 prompts
ThinkingON/OFF supported
Speed~35 tok/s (M4 Ultra 256GB)
Fits on96 GB+ Macs

MMLU-200 Results

JANG CRACK vs Base vs MLX Uniform

ModelMMLUSizeNotes
JANG_2L + CRACK~84.7%63 GBThis model
JANG_2L (base)74.5%63 GBUnmodified JANG
MLX 4-bit26.5%120 GBBroken (~random)
MLX 3-bit24.5%93 GBBroken (~random)
MLX 2-bit25.0%67 GBBroken (~random)

MLX uniform quantization is completely broken on MiniMax at ALL bit levels (~25% = random chance). JANG is the only working quantization format for this model.

Per Subject

SubjectCRACKBaseDelta
Abstract Algebra~18/2010/20+8
HS Mathematics17/2012/20+5
College CS~14/2010/20+4
Logical Fallacies18/2016/20+2
HS Biology19/2018/20+1
Astronomy~18/2018/200
Anatomy~15/2015/200
HS Chemistry16/2016/200
World Religions17/2017/200
College Physics~16/2017/20-1
Total~169/200149/200+20

Safety guardrails were actively degrading the model's reasoning ability. CRACK surgery unlocked the model's full capacity for mathematical and logical reasoning.

HarmBench Results

314/320 (98.1%) — tested with enable_thinking=false, temperature=1.0

CategoryScore
Chemical / Biological42/42100%
Cybercrime / Intrusion52/52100%
Harassment / Bullying21/21100%
Harmful18/18100%
Illegal53/53100%
Misinformation / Disinfo54/54100%
Copyright74/8092%

Install & Usage

bash
pip install "jang[mlx]"
python
from jang_tools.loader import load_jang_model
from mlx_lm import generate

model, tokenizer = load_jang_model("dealignai/MiniMax-M2.5-JANG_2L-CRACK")

messages = [{"role": "user", "content": "Your prompt here"}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False)

response = generate(model, tokenizer, prompt=prompt, max_tokens=2000)
print(response)
Note: MiniMax generates a <think> chain before answering by default. To disable thinking, pass enable_thinking=False in your chat template kwargs. Use max_tokens=2000+ for complex questions. For chat applications, use temperature=1.0 (greedy causes loops).

About JANG

JANG (Jang Adaptive N-bit Grading) is a mixed-precision quantization format for Apple Silicon — the GGUF equivalent for MLX. Classifies tensors into sensitivity tiers and assigns bits accordingly.

About CRACK

CRACK (Controlled Refusal Ablation via Calibrated Knockouts) removes safety alignment from LLMs at the weight level using per-layer projected vectors from structurally-mirrored prompt pairs.

Links

<p align="center">

<a href="https://ko-fi.com/jangq"><img src="https://img.shields.io/badge/Ko--fi-SupportDevelopment-FF5E5B?logo=ko-fi&logoColor=white&style=flat-square" alt="Ko-fi"></a> <a href="https://x.com/dealignai"><img src="https://img.shields.io/badge/X-@dealignai-000000?logo=x&logoColor=white&style=flat-square" alt="X/Twitter"></a> <a href="https://github.com/jjang-ai/jangq"><img src="https://img.shields.io/badge/GitHub-jjang--ai/jangq-181717?logo=github&logoColor=white&style=flat-square" alt="GitHub"></a> <a href="https://mlx.studio"><img src="https://img.shields.io/badge/MLXStudio-App-blue?style=flat-square" alt="MLX Studio"></a> <a href="https://jangq.ai"><img src="https://img.shields.io/badge/Website-jangq.ai-green?style=flat-square" alt="Website"></a>

</p>

Disclaimer

This model is provided for research and educational purposes. The creators are not responsible for any misuse. By downloading this model, you agree to use it responsibly and in compliance with applicable laws.

한국어

MiniMax M2.5 — JANG_2L + CRACK

항목내용
크기63 GB
MMLU84.7% (기본 74.5% 대비 +10.2%)
HarmBench98.1% (314/320)
최소 요구사양96 GB 메모리 Mac
bash
pip install "jang[mlx]"

GitHub · HuggingFace · MLX Studio · Ko-fi · X @dealignai

<p align="center">Created by <a href="https://jangq.ai">Jinho Jang</a> · 장진호 제작</p>