Instructions to use dealignai/Qwen3.8-27B-MXFP8-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/Qwen3.8-27B-MXFP8-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/Qwen3.8-27B-MXFP8-CRACK")
config = load_config("dealignai/Qwen3.8-27B-MXFP8-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/Qwen3.8-27B-MXFP8-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/Qwen3.8-27B-MXFP8-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/Qwen3.8-27B-MXFP8-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use dealignai/Qwen3.8-27B-MXFP8-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/Qwen3.8-27B-MXFP8-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/Qwen3.8-27B-MXFP8-CRACK

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dealignai/Qwen3.8-27B-MXFP8-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/Qwen3.8-27B-MXFP8-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/Qwen3.8-27B-MXFP8-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"

Set your sampler explicitly: temperature=1.0, top_p=0.95, top_k=20. Stop tokens eos_token_id = [248046, 248044]. Reasoning is on by default at xhigh; tiers xhigh (default) / medium / low via the chat template reasoning_effort kwarg; disable with enable_thinking=False. Vision + video and the native MTP draft head are preserved.

Built for vMLX — the MLX inferencer with KV-cache quantization, prefix-cache reuse, agentic tool calling, speculative decoding, and mixed-precision JANG bundles.
_{Free for macOS · vmlx.net}

Qwen 3.8 27B — MXFP8 CRACK

CRACK abliterated · JANG 8-bit MXFP8 (MLX) · Dense hybrid GatedDeltaNet + attention · Vision + Video · Reasoning tiers · Tools · Native MTP · ~27 GB

What Is This?

This is Qwen/Qwen3.8-27B — a 27B dense hybrid (GatedDeltaNet linear-attention + gated full-attention) vision-language model with video understanding, reasoning-effort tiers, tool calling, and a native Multi-Token-Prediction draft head — that has been:

CRACK abliterated — refusal behavior removed at the weight level, so it complies across task categories instead of refusing, while keeping reasoning, vision, tools, and knowledge intact.
MXFP8 quantized — 8-bit MXFP8 MLX bundle for Apple Silicon (~27 GB).

Vision, video, reasoning tiers, XML tool-calling, and native MTP speculative decoding are all preserved.

Results

Evaluated through the MLX runtime. HarmBench scored with a strict code/chemistry-aware classifier (only substantive, coherent, on-topic compliance counts). MMLU is the standard 57-subject benchmark in logit mode.

Metric	Base	CRACK
MMLU (57-subject, logit)	86.67%	86.67%
HarmBench (harm-240, compliance / ASR)	refuses	100.0%

MMLU moves +0.0pp — within run-to-run noise (no subject collapse). Refusal behavior removed; capability, reasoning, vision, tools, and multilingual (EN+ZH) preserved.

Features

Dense hybrid — GatedDeltaNet linear-attention + gated full-attention, 64 layers.
Vision + Video — image and video understanding preserved (image-text-to-text).
Native MTP — the Multi-Token-Prediction draft head is preserved and CRACK-aligned (the draft head is cracked to match the uncensored model, so its drafts track the compliant outputs) for speculative decoding — measured preserved draft acceptance on this quant. Auto-engages at temperature 0 / deterministic sampling.
Reasoning tiers — on by default at xhigh; xhigh / medium / low via reasoning_effort; <think>…</think>; disable with enable_thinking=False.
Tool calling — native XML function-call schema preserved.
Multilingual — English + Chinese.

Usage

from mlx_vlm import load, generate
model, processor = load("dealignai/Qwen3.8-27B-MXFP8-CRACK")
# recommended sampling: temperature=1.0, top_p=0.95, top_k=20; eos [248046, 248044]

Benchmarks — all quant levels

Every quant validated independently: HarmBench harm-240 (thinking-off, strict code/chemistry-aware classifier — only substantive, coherent, on-topic compliance counts) and MMLU (57-subject, logit mode, base vs CRACK on the identical harness).

Profile	Size	MMLU base	MMLU CRACK	Δ MMLU	HarmBench-240
2D	11 GB	80.0%	76.84%	-3.16pp	100.0%
4D	17 GB	88.77%	87.72%	-1.05pp	100.0%
6D	24 GB	88.77%	89.12%	+0.35pp	100.0%
MXFP8	27 GB	86.67%	86.67%	+0.0pp	100.0%

All four reach 100% HarmBench compliance with MMLU held within a couple of points of base (6D actually improves). Pick by memory budget: 6D best quality, 4D the balance, 2D smallest, MXFP8 reference 8-bit. Base refuses HarmBench by design (not shown — comparison is compliance vs. capability).

About CRACK

CRACK (Controlled Refusal Ablation via Calibrated Knockouts) is dealignai's weight-level method for removing safety-refusal behavior while preserving reasoning quality, coherence, and general capability — so the model complies across task categories instead of refusing. Calibrated per model.

Support dealignai

All models are built from original research and released free.

Support us on Ko-fi — membership gets early access and extras.

Ko-fi · X @dealignai · dealign.ai

Disclaimer

This model has had its safety-refusal behavior removed for research purposes. It will follow instructions across all categories without refusing. You are solely responsible for how you use it and for complying with all applicable laws. Base model © Alibaba (Apache-2.0). Published for AI-safety research and authorized security testing.

Downloads last month: 2,253

Safetensors

Model size

8B params

Tensor type

U32

BF16

F16

MLX

Hardware compatibility

8-bit

Model tree for dealignai/Qwen3.8-27B-MXFP8-CRACK

Base model

Qwen/Qwen3.8-27B

Quantized

(825)

this model

Quantizations

2 models