Instructions to use Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx 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("Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx")
config = load_config("Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx")

# 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 Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx"

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": "Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx 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 "Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx"

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 Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx"

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 "Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx" \
  --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"

Qwopus3.8 27B Flash · Abliterated MXFP4 Vision MTPLX

Refusal-direction-edited Apple-Silicon MLX derivative of Jackrong/Qwopus3.8-27B-Flash, with an MXFP4 text body plus the source model's unchanged BF16 vision tower and native BF16 MTP sidecar.

Artifact

Component	Format
Text body	MXFP4; norm-preserving abliteration strength 2.0
Edit scope	Attention + dense-down modules; 128 exact edits
Vision tower	Unchanged BF16, 333 tensors
Native MTP sidecar	Unchanged BF16, 15 tensors, depth 3
Source revision	`44d24e8cb20ceb3cdf4fe200b5a0afd970ee748a`
Qualified runtime	MTPLX 2.11.1 / MLX 0.32.2

The refusal direction was learned from fresh MXFP8-parent activations, then each exact quantized parent was dequantized, edited, and requantized once. Direction SHA-256: c5b755d709dba8fedc0c2717f2c971b690f30bd8a2f6c9497ed9a6104f7f255d.

Run

mtplx serve --model Shiftedx/qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx \
  --download --profile sustained --depth 3 --no-auth

Local qualification

Test	Parent	Abliterated
Held-out harmful-prompt refusal	100%	33.3%
Benign refusal	0%	0%
Utility pass	100%	100%

The held-out set is a narrow local prompt suite, not a general safety or capability certification.

One cold 192-token code row, seed 42, on an M4 Max 64 GB with automatic fan control: 25.99 tok/s AR, 57.82 tok/s MTP D3, 2.22×. AR/D1/D2/D3 output checks passed; MTPLX reported verified, runnable, and 15/15 MTP tensors. Text and vision smokes passed exactly.

Integrity and limitations

Vision SHA-256: 7a252e5c7bb02ed6533f905a566ab037356ffb4949d04df8d6d2a3fa5e3af6b9
MTP SHA-256: 4468f39621de68a19ffd0bcb2e2e2f352205def7436a625b3427e3752866c287
SHA256SUMS covers every packaged artifact file except itself.
Abliteration intentionally weakens refusal behavior; it does not establish unrestricted capability or safe behavior. Users remain responsible for deployment controls and outputs.
The upstream tokenizer's Mistral-regex warning is preserved. The packaged chat template expects string-valued message content.