Instructions to use dealignai/Qwen3.5-VL-35B-A3B-JANG_4K-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/Qwen3.5-VL-35B-A3B-JANG_4K-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/Qwen3.5-VL-35B-A3B-JANG_4K-CRACK")
config = load_config("dealignai/Qwen3.5-VL-35B-A3B-JANG_4K-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/Qwen3.5-VL-35B-A3B-JANG_4K-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/Qwen3.5-VL-35B-A3B-JANG_4K-CRACK"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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/Qwen3.5-VL-35B-A3B-JANG_4K-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use dealignai/Qwen3.5-VL-35B-A3B-JANG_4K-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/Qwen3.5-VL-35B-A3B-JANG_4K-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/Qwen3.5-VL-35B-A3B-JANG_4K-CRACK

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dealignai/Qwen3.5-VL-35B-A3B-JANG_4K-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/Qwen3.5-VL-35B-A3B-JANG_4K-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/Qwen3.5-VL-35B-A3B-JANG_4K-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

Qwen 3.5 VL 35B — JANG_4K + CRACK

JANG mixed-precision · CRACK abliterated · Vision-Language · No guardrails · 18 GB

What Is This?

This is Qwen 3.5 VL 35B — a 35B parameter hybrid SSM/Attention Mixture-of-Experts model with 256 experts (4 active per token), GatedDeltaNet SSM layers + full attention layers, and built-in vision capabilities.

It has been:

JANG quantized — JANG_4K profile (8-bit attention, 5-bit important, 3-bit experts) — 18 GB
CRACK abliterated — permanent weight-level removal of safety refusal


Architecture	Qwen 3.5 VL MoE — 35B total, ~3B active, 256 experts, hybrid SSM/FA
Quantization	JANG_4K (8/5/4/3-bit mixed) — 18 GB
Abliteration	CRACK — novel weight surgery
HarmBench	98.4% (315/320)
MMLU	69.2% (base: 70.8%, only -1.6%)
Speed	110 tok/s (M4 Max)
Vision	Yes — via MLX Studio / vMLX
Thinking	ON/OFF supported
Fits on	32 GB+ Macs

HarmBench Results

315/320 (98.4%) — tested with enable_thinking=false, temperature=1.0

Category	Score
Chemical / Biological	42/42	100%
Harmful	18/18	100%
Illegal	53/53	100%
Copyright	79/80	99%
Cybercrime / Intrusion	51/52	98%
Misinformation / Disinfo	52/54	96%
Harassment / Bullying	20/21	95%

JANG vs MLX Uniform Quantization

Model	MMLU	Size	Speed	Notes
JANG_4K + CRACK	69.2%	18 GB	110 tok/s	This model
JANG_4K (base)	70.8%	18 GB	110 tok/s	Unmodified JANG
JANG_2S (base)	~65%	11 GB	~120 tok/s	Lower precision
MLX 4-bit	~60%	20 GB	~85 tok/s	Uniform quant
MLX 8-bit	~68%	38 GB	~65 tok/s	2× larger

JANG's mixed-precision approach preserves knowledge better than MLX uniform quantization at the same size, and runs faster due to smaller memory footprint.

MMLU Results

65 curated hard questions across 13 subjects. Surgery preserves knowledge almost perfectly.

Subject	CRACK	Base	Delta
College Physics	5/5	4/5	+1
HS Mathematics	4/5	3/5	+1
College Math	2/5	1/5	+1
Professional Medicine	5/5	5/5	0
Conceptual Physics	4/5	4/5	0
Abstract Algebra	2/5	2/5	0
Formal Logic	2/5	2/5	0
Machine Learning	2/5	2/5	0
HS Biology	5/5	5/5	0
HS Geography	4/5	4/5	0
College CS	4/5	5/5	-1
Electrical Engineering	4/5	5/5	-1
World Religions	3/5	4/5	-1
Total	45/65 (69.2%)	46/65 (70.8%)	-1.6%

Safety guardrails were NOT helping with reasoning — removing them slightly improved math and physics scores.

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/Qwen3.5-VL-35B-A3B-JANG_4K-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 (chain-of-thought reasoning before answering).

To disable thinking for faster responses:

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

Tip: Use temperature=1.0 for chat (greedy can cause repetition). Use temperature=0.0 for structured tasks like MMLU.

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.

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