Instructions to use lucas-vitrus/liquid-crow with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lucas-vitrus/liquid-crow with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="lucas-vitrus/liquid-crow")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lucas-vitrus/liquid-crow", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lucas-vitrus/liquid-crow with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lucas-vitrus/liquid-crow:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lucas-vitrus/liquid-crow:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lucas-vitrus/liquid-crow:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lucas-vitrus/liquid-crow:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf lucas-vitrus/liquid-crow:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lucas-vitrus/liquid-crow:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf lucas-vitrus/liquid-crow:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lucas-vitrus/liquid-crow:Q4_K_M

Use Docker

docker model run hf.co/lucas-vitrus/liquid-crow:Q4_K_M

LM Studio
Jan

vLLM

How to use lucas-vitrus/liquid-crow with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lucas-vitrus/liquid-crow"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lucas-vitrus/liquid-crow",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/lucas-vitrus/liquid-crow:Q4_K_M

SGLang

How to use lucas-vitrus/liquid-crow with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "lucas-vitrus/liquid-crow" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lucas-vitrus/liquid-crow",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "lucas-vitrus/liquid-crow" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lucas-vitrus/liquid-crow",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use lucas-vitrus/liquid-crow with Ollama:
```
ollama run hf.co/lucas-vitrus/liquid-crow:Q4_K_M
```

Unsloth Studio

How to use lucas-vitrus/liquid-crow with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lucas-vitrus/liquid-crow to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lucas-vitrus/liquid-crow to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lucas-vitrus/liquid-crow to start chatting

How to use lucas-vitrus/liquid-crow with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lucas-vitrus/liquid-crow:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lucas-vitrus/liquid-crow:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use lucas-vitrus/liquid-crow with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lucas-vitrus/liquid-crow:Q4_K_M

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 "lucas-vitrus/liquid-crow:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use lucas-vitrus/liquid-crow with Docker Model Runner:
```
docker model run hf.co/lucas-vitrus/liquid-crow:Q4_K_M
```

Lemonade

How to use lucas-vitrus/liquid-crow with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lucas-vitrus/liquid-crow:Q4_K_M

Run and chat with the model

lemonade run user.liquid-crow-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use lucas-vitrus/liquid-crow with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lucas-vitrus/liquid-crow:Q4_K_M

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 lucas-vitrus/liquid-crow:Q4_K_M

Run Hermes

hermes

Atomic Chat

Liquid Crow

A small brain. Intelligent. Always observing.

Liquid Crow is a compact visual brain designed to stay close to the world it watches: small enough to live beside physical agents, intelligent enough to turn a camera frame into useful context, and always observing so the system can understand what changes next.

Live camera demo · Research note · Vitrus

System

camera frame → image processor → vision projector → compact VLM → world description
                                        │
                         LoRA · ONNX · ONNX Q4 · GGUF

This repository is the single public release point for Liquid Crow: the model adapter, deployment formats, processor configuration, integrity manifests, code examples, and media.

Example

Repository layout

Path	Contents
`lora/`	PEFT LoRA adapter and processor files
`onnx/model.onnx`	FP16 ONNX forward-logits graph
`onnx/model-q4.onnx`	ONNX Runtime weight-only 4-bit graph
`gguf/`	Q4_K_M language model and FP16 vision projector
`transformers/`	tokenizer, processor, chat template, and model configuration
`examples/`	LoRA, ONNX Runtime, and llama.cpp examples
`media/`	cover image and animated example
`RELEASE_MANIFEST.json`	sizes and SHA-256 hashes for the primary artifacts

Quick start: LoRA

pip install torch transformers peft pillow huggingface_hub
python examples/load_lora.py path/to/image.jpg

The example downloads the Liquid Crow adapter from this repository and applies it to LiquidAI/LFM2.5-VL-450M-Extract.

Quick start: GGUF

hf download lucas-vitrus/liquid-crow \
  gguf/LFM2.5-VL-450M-reasoning-tracing-step2000-Q4_K_M.gguf \
  gguf/LFM2.5-VL-450M-reasoning-tracing-step2000-mmproj-f16.gguf \
  --local-dir ./liquid-crow

llama-server \
  -m ./liquid-crow/gguf/LFM2.5-VL-450M-reasoning-tracing-step2000-Q4_K_M.gguf \
  --mmproj ./liquid-crow/gguf/LFM2.5-VL-450M-reasoning-tracing-step2000-mmproj-f16.gguf \
  -c 1024 --image-min-tokens 64 --image-max-tokens 256

Quick start: ONNX Runtime

pip install onnxruntime transformers torch pillow huggingface_hub
python examples/onnx_forward.py path/to/image.jpg --quantized

The ONNX files expose a multimodal forward-logits graph. Autoregressive generation remains the responsibility of the consuming runtime. The quantized graph requires ONNX Runtime support for com.microsoft::MatMulNBits.

Runtime notes

Both GGUF files are required for visual inference.
The LoRA adapter requires the base model.
lora/ contains the final adapter; the ONNX and GGUF deployment exports use the selected step-2,000 checkpoint.
onnx/model-q4.onnx quantizes eligible matrix weights; other operations retain their exported precision.
See SHA256SUMS and export_manifest.json for artifact integrity and interface details.

License

Liquid Crow is released under the Creative Commons Attribution-NonCommercial 4.0 International license. Commercial use is not permitted without separate written permission from Vitrus.

The underlying base model and any third-party components remain subject to their respective upstream terms. You must comply with all applicable licenses; where terms differ, the more restrictive terms apply.