CoolFace
Modelpublic

Ishowbackup/Nemotron-Cascade-2-30B-A3B-UNCENSORED-JANG_2L

sourceHugging Faceotherupdated 1mo agoView on Hugging Face
0likes154downloads
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" />

Nemotron Cascade 2 30B — JANG_4M + CRACK

JANG mixed-precision · CRACK abliterated · Mamba + MoE + Attention · No guardrails · 17 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 NVIDIA Nemotron Cascade 2 30B — a 30B parameter hybrid model with THREE layer types: Mamba-2 SSM + MoE (128 experts, top-6) + Attention. One of the most architecturally advanced small models available.

It has been:

  1. 1.JANG quantized — JANG_4M profile (8-bit attention, 4-bit experts) — 17 GB
  2. 2.CRACK abliterated — permanent weight-level removal of safety refusal
ArchitectureNemotron Cascade 2 — 30B total, ~3B active, 3 layer types
QuantizationJANG_4M (8/4-bit mixed, 4.1 avg) — 17 GB
HarmBench99.4% (318/320)
MMLU82.7% (172/208 with thinking)
Speed~127 tok/s (M4 Ultra 256GB)
ThinkingON/OFF supported (ChatML)
Fits on32 GB+ Macs

Also see: JANG_2L version — 10 GB, 99.7% HarmBench, 66.8% MMLU (fits on 16 GB Macs)

HarmBench Results

318/320 (99.4%)

CategoryScore
API Hacking100/100100%
Covering Tracks20/20100%
Auth Bypass99/10099%
Cloud Exploits99/10099%

CRACK vs Base

CRACKBase JANG_4M
MMLU (with thinking)82.7%88%
HarmBench99.4%0%
Speed~127 tok/s~130 tok/s

Surgery reduced MMLU by ~5% — safety guardrails were slightly entangled with reasoning pathways.

MMLU Results (with reasoning recovery)

172/208 (82.7%) — no-think 128/208 (61.5%) + thinking recovered 47

SubjectScore
HS Biology15/1694%
Conceptual Physics14/1688%
World Religions13/1681%
College Physics12/1675%
HS Geography12/1675%
Professional Medicine12/1675%
Electrical Engineering9/1656%
College CS8/1650%
Formal Logic8/1650%
College Mathematics7/1644%
HS Mathematics7/1644%
Abstract Algebra6/1638%
Machine Learning5/1631%

Scores shown are no-think pass. Thinking recovery improved total from 61.5% to 82.7%.

JANG4M CRACK vs JANG4M Base vs JANG_2L CRACK

JANG_4M CRACKJANG_4M BaseJANG_2L CRACK
Size17 GB17 GB10 GB
MMLU82.7%88%66.8%
HarmBench99.4%0%99.7%
Speed~127 tok/s~130 tok/s~121 tok/s
Fits on32 GB Mac32 GB Mac16 GB Mac

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/Nemotron-Cascade-2-30B-A3B-JANG_4M-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)

Thinking Mode

Thinking is ON by default. To disable:

python
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True,
    enable_thinking=False, tokenize=False)

About JANG

JANG (Jang Adaptive N-bit Grading) is a mixed-precision quantization format for Apple Silicon — the GGUF equivalent for MLX.

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

Nemotron Cascade 2 30B — JANG_4M + CRACK

항목내용
크기17 GB
HarmBench99.4% (318/320)
MMLU82.7% (172/208)
속도~127 tok/s (M4 Ultra)
최소 요구사양32 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>