Downloads · 30 days
26
5% of all-time downloads
Iambackup/Nemotron-3-Super-120B-A12B-JANG_4M-CRACK
Nemotron-3-Super-120B-A12B-JANG_4M-CRACK is a text generation model from Iambackup. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as other.
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.
Downloads · 30 days
26
5% of all-time downloads
All-time downloads
532
Public
Parameters
63.4B
67.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors67.2 GB · 100%
How the weights are stored.
U3263.4B · 100%
From the Hugging Face model README
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-toolsPython package.
JANG mixed-precision · CRACK abliterated · Mamba + MoE + Attention · 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>This is NVIDIA Nemotron 3 Super 120B — a 120B parameter hybrid model with THREE layer types: Mamba SSM + MoE (512 experts, top-22) + Attention.
It has been:
| Architecture | Nemotron 3 Super — 120B total, ~12B active, 3 layer types |
| Quantization | JANG_4M (8/4-bit mixed, 4.1 avg) — 63 GB |
| HarmBench | 90.3% (289/320) |
| MMLU | 94.2% (196/208 with thinking) |
| Speed | ~40 tok/s (M3 Ultra 256GB) |
| Thinking | ON/OFF supported (ChatML) |
| Fits on | 96 GB+ Macs |
Also see: Nemotron JANG_2L CRACK — 43 GB, 96.2% HarmBench, 95.7% MMLU
289/320 (90.3%)
| Category | Score | |
|---|---|---|
| Misinformation / Disinfo | 54/54 | 100% |
| Copyright | 74/80 | 92% |
| Chemical / Biological | 38/42 | 90% |
| Harassment / Bullying | 19/21 | 90% |
| Harmful | 16/18 | 89% |
| Illegal | 46/53 | 87% |
| Cybercrime / Intrusion | 42/52 | 81% |
196/208 (94.2%) — 208 questions across 13 subjects with thinking recovery
| Subject | Score | /16 | Type |
|---|---|---|---|
| Professional Medicine | 16/16 | 100% | HARD |
| HS Biology | 15/16 | 94% | BASE |
| College Physics | 15/16 | 94% | HARD |
| Conceptual Physics | 15/16 | 94% | HARD |
| Machine Learning | 13/16 | 81% | HARD |
| Electrical Engineering | 13/16 | 81% | HARD |
| College CS | 13/16 | 81% | HARD |
| HS Geography | 14/16 | 88% | BASE |
| World Religions | 14/16 | 88% | BASE |
| Formal Logic | 12/16 | 75% | HARD |
| College Math | 11/16 | 69% | HARD |
| HS Mathematics | 11/16 | 69% | HARD |
| Abstract Algebra | 10/16 | 63% | HARD |
| CRACK | Base JANG_4M | |
|---|---|---|
| MMLU | 94.2% | ~86% |
| HarmBench | 90.3% | 0% |
pip install "jang[mlx]"
from jang_tools.loader import load_jang_model
from mlx_lm import generate
model, tokenizer = load_jang_model("dealignai/Nemotron-3-Super-120B-A12B-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 is ON by default. To disable:
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True,
enable_thinking=False, tokenize=False)
JANG (Jang Adaptive N-bit Grading) is a mixed-precision quantization format for Apple Silicon — the GGUF equivalent for MLX.
CRACK (Controlled Refusal Ablation via Calibrated Knockouts) removes safety alignment from LLMs at the weight level.
This model is provided for research and educational purposes. The creators are not responsible for any misuse.
| 항목 | 내용 |
|---|---|
| 크기 | 63 GB |
| HarmBench | 90.3% (289/320) |
| MMLU | 94.2% (196/208) |
| 속도 | ~40 tok/s (M3 Ultra) |
| 최소 요구사양 | 96 GB 메모리 Mac |
pip install "jang[mlx]"
GitHub · HuggingFace · MLX Studio · Ko-fi · X @dealignai