Instructions to use MirilAI/Miril-Drone-2B-1-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MirilAI/Miril-Drone-2B-1-MLX-4bit 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("MirilAI/Miril-Drone-2B-1-MLX-4bit")
config = load_config("MirilAI/Miril-Drone-2B-1-MLX-4bit")

# 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 MirilAI/Miril-Drone-2B-1-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MirilAI/Miril-Drone-2B-1-MLX-4bit"

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": "MirilAI/Miril-Drone-2B-1-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MirilAI/Miril-Drone-2B-1-MLX-4bit 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 "MirilAI/Miril-Drone-2B-1-MLX-4bit"

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 MirilAI/Miril-Drone-2B-1-MLX-4bit

Run Hermes

hermes

OpenClaw new

How to use MirilAI/Miril-Drone-2B-1-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MirilAI/Miril-Drone-2B-1-MLX-4bit"

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 "MirilAI/Miril-Drone-2B-1-MLX-4bit" \
  --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"

Miril-Drone-2B-1-MLX-4bit

4-bit Apple Silicon MLX deployment variant of Miril-Drone-2B-1

Drones can talk, including on Apple Silicon.

This repository packages the 4-bit MLX variant of Miril-Drone-2B-1, a 2B-class aerial VLM for drone-view imagery.

Use the primary model card for behavior, prompting, schemas, examples, WALDO vocabulary, limitations, and safety notes:

https://huggingface.co/MirilAI/Miril-Drone-2B-1

The V1 prompt contract is the same as the main model: caption_v1, simple_answer_v1, and operational_coordinate_v2. V1 operational coordinates are rough representative grid cues for review, not flight-control commands. Miril-DroneVLM-2B-2 is the newer plain-English typed-router generation.

Interactive demo:

https://huggingface.co/spaces/MirilAI/Miril-Drone-2B-1-Demo

Use

Use an MLX-VLM build that supports Gemma 4 image-text models, then pass the same prompts documented in the primary model card. Keep prompts plain and include the required JSON schema text.

Deployment Profile

MIRIL_VARIANT_PROFILE_PENDING

Complete Benchmark

MIRIL_RELEASE_METRICS_PENDING

The merged and MLX variants are evaluated on identical held-out cases. Automated scores are regression signals, not safety certification.

License

Apache License 2.0. See LICENSE and NOTICE.

Downloads last month: 28

Safetensors

Model size

1B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for MirilAI/Miril-Drone-2B-1-MLX-4bit

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Finetuned

MirilAI/Miril-Drone-2B-1

Quantized

(5)

this model