Instructions to use LiquidAI/LFM3-VL-2B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM3-VL-2B-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("LiquidAI/LFM3-VL-2B-MLX-4bit")
config = load_config("LiquidAI/LFM3-VL-2B-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 LiquidAI/LFM3-VL-2B-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 "LiquidAI/LFM3-VL-2B-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": "LiquidAI/LFM3-VL-2B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use LiquidAI/LFM3-VL-2B-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 "LiquidAI/LFM3-VL-2B-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 LiquidAI/LFM3-VL-2B-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LiquidAI/LFM3-VL-2B-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 "LiquidAI/LFM3-VL-2B-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 "LiquidAI/LFM3-VL-2B-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"

API Try Docs Blog

LFM3-VL-2B-MLX-4bit

4-bit MLX version of LFM3-VL-2B for Apple Silicon. The weights take 1.59 GB.

Weights use 4-bit affine quantization with groups of 32. Token embeddings stay in 8-bit. The weights are trained with quantization-aware distillation (QAD), so they recover much of the 8-bit performance.

Find architecture and usage details in the original model card.

Use with MLX-VLM

Requires MLX-VLM 0.7.11 or later:

pip install -U "mlx-vlm>=0.7.11"

python -m mlx_vlm.generate --model LiquidAI/LFM3-VL-2B-MLX-4bit \
  --image <IMAGE PATH> --prompt "Describe this image." --enable-thinking \
  --temperature 0.1 --top-p 1.0 --top-k 50 --min-p 0.0 --repetition-penalty 1.1 \
  --max-tokens 16384

Reasoning stays off unless you pass --enable-thinking. More options in the MLX guide.

Downloads last month: 2,854

Safetensors

Model size

2B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for LiquidAI/LFM3-VL-2B-MLX-4bit

Base model

LiquidAI/LFM3-1.7B-Base

Finetuned

LiquidAI/LFM3-VL-2B

Quantized

(34)

this model