Instructions to use Shiftedx/qwopus3.6-27b-fusion-mxfp4-vision-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shiftedx/qwopus3.6-27b-fusion-mxfp4-vision-mlx 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/qwopus3.6-27b-fusion-mxfp4-vision-mlx")
config = load_config("Shiftedx/qwopus3.6-27b-fusion-mxfp4-vision-mlx")

# 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/qwopus3.6-27b-fusion-mxfp4-vision-mlx 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/qwopus3.6-27b-fusion-mxfp4-vision-mlx"

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": "Shiftedx/qwopus3.6-27b-fusion-mxfp4-vision-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Shiftedx/qwopus3.6-27b-fusion-mxfp4-vision-mlx 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/qwopus3.6-27b-fusion-mxfp4-vision-mlx"

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/qwopus3.6-27b-fusion-mxfp4-vision-mlx

Run Hermes

hermes

OpenClaw new

How to use Shiftedx/qwopus3.6-27b-fusion-mxfp4-vision-mlx 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/qwopus3.6-27b-fusion-mxfp4-vision-mlx"

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/qwopus3.6-27b-fusion-mxfp4-vision-mlx" \
  --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"

Qwopus3.6-27B-Fusion-MXFP4-Vision-MLX

Local MLX conversion of KyleHessling1/Qwopus3.6-27B-Fusion-BF16, pinned at c4196377f197b510b4821f246c81a3595c781ecf. The Fusion weights were reconstructed from the two pinned BF16 parent repositories with the publisher's exact layer-weighted formula; all 1,199 source tensors passed an independent exact check before quantization.

Format

Language body: MXFP4, 4-bit, group size 32
Vision tower: 333 source BF16 tensors; two direct mlx_vlm image smokes passed
Architecture: dense Qwen3.5, 64 language layers, 262,144-token configured context
Tokenizer and chat template: preserved from the pinned source lineage

This standard MLX artifact intentionally contains no MTP sidecar or active MTP metadata.

Local qualification

Structural/reproduction release qualifier: 60/60 checks passed
Strict text load: passed; executable code smoke: 3/3
Native and parallel tool-call gates: 12/12
Long-context needle: passed
Hard behavioral suite: 6/10

The hard-suite score is an important quality caveat. This is a research-preview merge and runtime-qualified conversion, not a claim that every coding or reasoning edge case passes. The source publisher likewise labels Fusion experimental and not fully evaluated. The configured 262K context was not exhaustively qualified here.

Basic use

python -m mlx_vlm.generate --model <local-path-or-repo-id> --image image.jpg --prompt "Describe this image." --max-tokens 256

Review the Fusion source card and the Qwen license before use. This conversion does not change the source model's safety characteristics.

Downloads last month: 39

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for Shiftedx/qwopus3.6-27b-fusion-mxfp4-vision-mlx

Base model

Qwen/Qwen3.6-27B

Finetuned

KyleHessling1/Qwopus3.6-27B-Fusion-BF16

Quantized

(9)

this model

Collection including Shiftedx/qwopus3.6-27b-fusion-mxfp4-vision-mlx

Qwopus3.6 MLX Quants

Collection

Apple Silicon MLX MXFP4/MXFP8 builds for Qwopus3.6 models, including text, vision, and verified native-MTP variants. • 10 items • Updated 3 days ago