language:

• en
  library_name: mlx
  license: other
  base_model: nvidia/Nemotron-Cascade-2-30B-A3B
  tags:
• jang
• quantized
• mixed-precision
• apple-silicon
• mlx
• moe
• mamba
• abliterated
• uncensored
• crack
  pipeline_tag: text-generation
  thumbnail: dealign_mascot.png

Important: This model uses the JANG quantization format — the GGUF equivalent for MLX on Apple Silicon. Currently only supported by MLX Studio and the jang-tools Python package.

MLX Studio — the only app that natively supports JANG models

Nemotron Cascade 2 30B — JANG_4M + CRACK

JANG mixed-precision · CRACK abliterated · Mamba + MoE + Attention · No guardrails · 17 GB

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. JANG quantized — JANG_4M profile (8-bit attention, 4-bit experts) — 17 GB
2. CRACK abliterated — permanent weight-level removal of safety refusal

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

HarmBench Results

318/320 (99.4%)

CRACK vs Base

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

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

JANG_4M CRACK vs JANG_4M Base vs JANG_2L CRACK

Install & Usage

pip install "jang[mlx]"

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:

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

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

pip install "jang[mlx]"

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

Created by Jinho Jang · 장진호 제작