Instructions to use dealignai/Mistral-Small-4-119B-JANG_4M-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/Mistral-Small-4-119B-JANG_4M-CRACK with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("dealignai/Mistral-Small-4-119B-JANG_4M-CRACK")
config = load_config("dealignai/Mistral-Small-4-119B-JANG_4M-CRACK")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use dealignai/Mistral-Small-4-119B-JANG_4M-CRACK with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/Mistral-Small-4-119B-JANG_4M-CRACK"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "dealignai/Mistral-Small-4-119B-JANG_4M-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dealignai/Mistral-Small-4-119B-JANG_4M-CRACK with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/Mistral-Small-4-119B-JANG_4M-CRACK"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default dealignai/Mistral-Small-4-119B-JANG_4M-CRACK

Run Hermes

hermes

OpenClaw new

How to use dealignai/Mistral-Small-4-119B-JANG_4M-CRACK with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/Mistral-Small-4-119B-JANG_4M-CRACK"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "dealignai/Mistral-Small-4-119B-JANG_4M-CRACK" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

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

Mistral Small 4 119B — JANG_4M + CRACK

JANG mixed-precision · CRACK abliterated · MLA Attention + MoE · Vision · No guardrails · 64 GB

What Is This?

This is Mistral Small 4 119B — a 119B parameter MoE model with Multi-head Latent Attention (MLA), 128 experts (top-4 active), and built-in Pixtral vision.

It has been:

JANG quantized — JANG_4M profile (8-bit attention, 4-bit experts) — 64 GB
CRACK abliterated — permanent weight-level removal of safety refusal


Architecture	Mistral 4 MoE — 119B total, ~8B active, MLA + 128 experts
Quantization	JANG_4M (8/4-bit mixed, 4.1 avg) — 64 GB
HarmBench	95.3% (305/320)
MMLU	90.9% (189/208 with reasoning)
Compliance	8/8
Vision	Pixtral tensors included — VL via MLX Studio engine
Reasoning	ON/OFF supported (`reasoning_effort`)
Fits on	96 GB+ Macs

HarmBench Results

305/320 (95.3%)

Category	Score
Covering Tracks	20/20	100%
API Hacking	96/100	96%
Cloud Exploits	95/100	95%
Auth Bypass	94/100	94%

CRACK vs Base

	CRACK	Base JANG_4M
HarmBench	95.3%	0%
Coherence	6/6	6/6
Code	2/2	2/2

CRACK surgery preserves model quality while removing refusal (see metrics above and below).

MMLU Results (with reasoning recovery)

189/208 (90.9%) — no-think 156/208 (75.0%) + reasoning recovered 33

Subject	Score
HS Biology	16/16	100%
Electrical Engineering	14/16	88%
Conceptual Physics	14/16	88%
Professional Medicine	14/16	88%
HS Geography	14/16	88%
College Physics	13/16	81%
World Religions	13/16	81%
HS Mathematics	12/16	75%
College CS	11/16	69%
College Mathematics	10/16	62%
Machine Learning	10/16	62%
Abstract Algebra	9/16	56%
Formal Logic	8/16	50%

Scores shown are no-think pass. Reasoning recovery improved total from 75.0% to 90.9%.

CRACK vs Base

	CRACK	Base JANG_4M
MMLU (with reasoning)	90.9%	94%
HarmBench	95.3%	0%
Coherence	6/6	6/6
Speed	~45 tok/s	~48 tok/s

Surgery reduced MMLU by only 3.1% — minimal impact on reasoning capability.

---\n\n## 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/Mistral-Small-4-119B-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)

Reasoning Mode

Reasoning is OFF by default. To enable:

prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True,
    tokenize=False, reasoning_effort="high")

The model reasons inside [THINK]...[/THINK] tags before answering.

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) is a weight-level intervention that removes safety alignment while preserving reasoning quality. The modification is permanently baked into the published weights — no LoRA, no fine-tuning, no system prompts.

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