Instructions to use LiquidAI/LFM2.5-VL-3B-MLX-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2.5-VL-3B-MLX-5bit 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/LFM2.5-VL-3B-MLX-5bit")
config = load_config("LiquidAI/LFM2.5-VL-3B-MLX-5bit")

# 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/LFM2.5-VL-3B-MLX-5bit 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/LFM2.5-VL-3B-MLX-5bit"

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": "LiquidAI/LFM2.5-VL-3B-MLX-5bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use LiquidAI/LFM2.5-VL-3B-MLX-5bit 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/LFM2.5-VL-3B-MLX-5bit"

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/LFM2.5-VL-3B-MLX-5bit" \
  --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"

Hermes Agent

How to use LiquidAI/LFM2.5-VL-3B-MLX-5bit 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/LFM2.5-VL-3B-MLX-5bit"

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/LFM2.5-VL-3B-MLX-5bit

Run Hermes

hermes

Atomic Chat

LFM2.5-VL-3B-MLX-5bit / README.md

samuelstevens

Initial release

ee622a3 1 day ago

preview code

Raw

History Blame Contribute Delete

2.14 kB

	---
	library_name: mlx
	license: other
	license_name: lfm1.0
	license_link: LICENSE
	language:
	- ar
	- zh
	- en
	- fr
	- de
	- hi
	- id
	- it
	- ja
	- ko
	- pl
	- pt
	- ru
	- es
	- th
	- vi
	pipeline_tag: image-text-to-text
	tags:
	- liquid
	- lfm2
	- lfm2-vl
	- edge
	- lfm2.5
	- lfm2.5-vl
	- mlx
	- mlx_vlm
	base_model: LiquidAI/LFM2.5-VL-3B
	---

	<div align="center">
	<img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%;">

	<p>
	<a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> •
	<a href="https://docs.liquid.ai/lfm"><strong>Documentation</strong></a> •
	<a href="https://leap.liquid.ai/"><strong>LEAP</strong></a> •
	<a href="https://www.liquid.ai/blog/"><strong>Blog</strong></a>
	</p>
	</div>

	# LFM2.5-VL-3B-MLX-5bit

	MLX export of [LFM2.5-VL-3B](https://huggingface.co/LiquidAI/LFM2.5-VL-3B) for Apple Silicon inference.

	LFM2.5-VL-3B is a vision-language model built on the LFM2.5-2.6B backbone with a SigLIP2 NaFlex vision encoder (400M).
	It supports OCR, document comprehension, multilingual vision understanding, bounding box prediction, and function calling.

	## Quickstart

	```bash
	uv run --with mlx-vlm mlx_vlm.generate --model LiquidAI/LFM2.5-VL-3B-MLX-5bit --max-tokens 100 --temperature 0.2 --image https://placecats.com/neo/300/200 --prompt "how many animals are in the picture?"
	```

	```python
	from mlx_vlm import apply_chat_template, generate, load
	from mlx_vlm.utils import load_image

	model, processor = load("LiquidAI/LFM2.5-VL-3B-MLX-5bit")

	image = load_image("https://placecats.com/neo/300/200")

	messages = [
	{
	"role": "user",
	"content": [
	{"type": "image"},
	{"type": "text", "text": "What do you see in this image?"},
	],
	}
	]
	prompt = apply_chat_template(
	processor,
	model.config,
	messages,
	add_generation_prompt=True,
	num_images=1,
	)

	result = generate(
	model,
	processor,
	prompt,
	[image],
	temp=0.2,
	top_k=50,
	repetition_penalty=1.0,
	verbose=True,
	)
	print(result.text)
	```