Instructions to use majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit 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("majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit")
config = load_config("majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit")

# 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 majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit"

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": "majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit 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 "majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit"

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 majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit

Run Hermes

hermes

OpenClaw new

How to use majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit"

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 "majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit" \
  --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"

GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit

6-bit MLX quantization of microsoft/GELab-Zero-4B-preview-Sico-Evolution — Microsoft's Qwen3-VL-based GUI agent (Edge / Copilot UI trajectories, from the Sico evolution pipeline) — running natively on Apple Silicon via mlx-vlm.

At a glance


Source	`microsoft/GELab-Zero-4B-preview-Sico-Evolution` @ `517c05402871b7c3020eab0925c7e0f9c2b02248`
Architecture	`Qwen3VLForConditionalGeneration` (36-layer text tower, 24-layer vision tower)
Format	MLX (Apple Silicon native), `mlx-vlm` loadable
Quantization	6-bit, group-size 64 (7.39 bits/weight effective)
Disk size	3.8 GB

Verification (2026-07-12, M-series Mac)

Converted with mlx-vlm 0.3.9 and image-inference smoke-tested locally before publishing — the BF16 source and this quantized pack both correctly describe the model's own benchmark chart:

"The image displays a bar chart comparing the Task Success Rate (TSR) of various models in Edge/Copilot test cases."

Sibling variants

Variant	Size	Status
GELab-Zero-4B-preview-Sico-Evolution-MLX-8bit	4.8 GB	public
GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit	3.8 GB	public
GELab-Zero-4B-preview-Sico-Evolution-MLX-4bit	2.9 GB	public

Usage

Requires mlx-vlm >= 0.3.9:

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

model, processor = load("majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit")
prompt = apply_chat_template(processor, model.config, "Describe this screenshot.", num_images=1)
print(generate(model, processor, prompt, ["screenshot.png"], max_tokens=256))

python -m mlx_vlm generate \
    --model majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit \
    --image screenshot.png --prompt "What action should I take next?"

Intended use

GUI-agent tasks — screenshot understanding, UI grounding, and next-action prediction for desktop/web automation — locally on Apple Silicon. This is the Edge/Copilot-evolved variant; see the base model card for benchmarks (82.9% TSR) and the Sico pipeline.

Reproduce

python -m mlx_vlm convert --hf-path microsoft/GELab-Zero-4B-preview-Sico-Evolution \
    --mlx-path GELab-6bit -q --q-bits 6 --q-group-size 64

License

Apache-2.0, inherited from the upstream model. This repository redistributes quantized weights with attribution; training and evaluation details are on the base model card.