Instructions to use gnukeith/Ocelot-1-VL-MLX-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gnukeith/Ocelot-1-VL-MLX-2bit 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("gnukeith/Ocelot-1-VL-MLX-2bit")
config = load_config("gnukeith/Ocelot-1-VL-MLX-2bit")

# 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 gnukeith/Ocelot-1-VL-MLX-2bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gnukeith/Ocelot-1-VL-MLX-2bit"

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": "gnukeith/Ocelot-1-VL-MLX-2bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use gnukeith/Ocelot-1-VL-MLX-2bit 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 "gnukeith/Ocelot-1-VL-MLX-2bit"

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 gnukeith/Ocelot-1-VL-MLX-2bit

Run Hermes

hermes

OpenClaw new

How to use gnukeith/Ocelot-1-VL-MLX-2bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gnukeith/Ocelot-1-VL-MLX-2bit"

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 "gnukeith/Ocelot-1-VL-MLX-2bit" \
  --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"

Ocelot-1-VL-MLX-2bit / README.md

gnukeith

Add files using upload-large-folder tool

797fab6 verified 9 days ago

preview code

Raw

History Blame Contribute Delete

1.18 kB

	---
	license: apache-2.0
	base_model: [bravesoftware/Ocelot-1-VL, Qwen/Qwen3-VL-4B-Instruct]
	library_name: mlx
	pipeline_tag: image-text-to-text
	tags: [mlx, qwen3-vl, vision, summarization, 2-bit]
	---

	# Ocelot-1-VL MLX 2-bit

	MLX 2-bit, group-size 64 conversion of [Ocelot-1-VL](https://huggingface.co/bravesoftware/Ocelot-1-VL), merged into its BF16 Qwen3-VL-4B-Instruct base. Effective quantization is 3.764 bits/weight because sensitive and unsupported tensors remain at higher precision.

	This model is specialized only for webpage summarization. Follow the strict prompt contract and limitations in the original model card. This maximum-compression variant has the greatest quality risk; prefer 4-bit unless memory is constrained.

	```bash
	pip install 'mlx-vlm @ git+https://github.com/Blaizzy/mlx-vlm.git'
	python -m mlx_vlm generate --model . --prompt 'The is the text of a webpage: <page>Page text here</page> Summarise the content between the <page> tags, or if no content is found use the screenshots provided, in the Brave Summary style.' --max-tokens 512
	```

	Converted with MLX-VLM revision `0b1d25e334686bd36dda71b2307d186dbb3e7859`. Text generation smoke test passed.