Instructions to use Lucasgitguy-co/lfm3-vl-2b-heretic-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lucasgitguy-co/lfm3-vl-2b-heretic-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("Lucasgitguy-co/lfm3-vl-2b-heretic-mlx-4bit")
config = load_config("Lucasgitguy-co/lfm3-vl-2b-heretic-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 Lucasgitguy-co/lfm3-vl-2b-heretic-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 "Lucasgitguy-co/lfm3-vl-2b-heretic-mlx-4bit"

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": "Lucasgitguy-co/lfm3-vl-2b-heretic-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use Lucasgitguy-co/lfm3-vl-2b-heretic-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 "Lucasgitguy-co/lfm3-vl-2b-heretic-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 Lucasgitguy-co/lfm3-vl-2b-heretic-mlx-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Lucasgitguy-co/lfm3-vl-2b-heretic-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 "Lucasgitguy-co/lfm3-vl-2b-heretic-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 "Lucasgitguy-co/lfm3-vl-2b-heretic-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"

LFM3-VL 2B Heretic — MLX 4-bit

4-bit MLX export for Apple Silicon of the LFM3-VL-2B Heretic checkpoint.

File	Size (decimal GB)
`model.safetensors`	1.352

Format and compatibility

The configuration specifies 4-bit affine quantization with group size 64. Use an MLX-VLM version with LFM3-VL support on Apple Silicon. These quantized weights require an MLX-compatible loader.

Download

pip install -U huggingface_hub
hf download Lucasgitguy-co/lfm3-vl-2b-heretic-mlx-4bit --local-dir ./lfm3-vl-2b-heretic-mlx-4bit

Related formats

For upstream model information and license terms, see LiquidAI/LFM3-VL-2B.

Evaluation and provenance

This card describes the repository files and configuration. Detailed training data, training procedure, and benchmark results are not documented in the inspected artifacts. Loading examples are guidance, not a claim of measured model quality.

License and attribution

The model weights, derived quantizations, and upstream model implementation remain subject to the LFM Open License v1.0 in LICENSE. Its commercial-use limitation applies to derivatives; this release is not an Apache-2.0 model. The publisher’s original documentation additions are available under Apache 2.0, without changing the terms of upstream material.

Repository guide

Downloads last month: 115

Safetensors

Model size

2B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for Lucasgitguy-co/lfm3-vl-2b-heretic-mlx-4bit

Base model

LiquidAI/LFM3-1.7B-Base

Finetuned

LiquidAI/LFM3-VL-2B

Finetuned

Lucasgitguy-co/lfm3-vl-2b-heretic

Quantized

(2)

this model