Instructions to use z-lab/Qwen3.5-2B-PARO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z-lab/Qwen3.5-2B-PARO with Transformers:

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

pipe = pipeline("image-text-to-text", model="z-lab/Qwen3.5-2B-PARO")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("z-lab/Qwen3.5-2B-PARO")
model = AutoModelForMultimodalLM.from_pretrained("z-lab/Qwen3.5-2B-PARO", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use z-lab/Qwen3.5-2B-PARO 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("z-lab/Qwen3.5-2B-PARO")
config = load_config("z-lab/Qwen3.5-2B-PARO")

# 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

vLLM

How to use z-lab/Qwen3.5-2B-PARO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "z-lab/Qwen3.5-2B-PARO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "z-lab/Qwen3.5-2B-PARO",
		"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/z-lab/Qwen3.5-2B-PARO

SGLang

How to use z-lab/Qwen3.5-2B-PARO 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 "z-lab/Qwen3.5-2B-PARO" \
    --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": "z-lab/Qwen3.5-2B-PARO",
		"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 "z-lab/Qwen3.5-2B-PARO" \
        --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": "z-lab/Qwen3.5-2B-PARO",
		"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"
						}
					}
				]
			}
		]
	}'

How to use z-lab/Qwen3.5-2B-PARO with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "z-lab/Qwen3.5-2B-PARO"

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": "z-lab/Qwen3.5-2B-PARO"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use z-lab/Qwen3.5-2B-PARO with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "z-lab/Qwen3.5-2B-PARO"

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 "z-lab/Qwen3.5-2B-PARO" \
  --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"

Docker Model Runner
How to use z-lab/Qwen3.5-2B-PARO with Docker Model Runner:
```
docker model run hf.co/z-lab/Qwen3.5-2B-PARO
```

Hermes Agent

How to use z-lab/Qwen3.5-2B-PARO 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 "z-lab/Qwen3.5-2B-PARO"

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 z-lab/Qwen3.5-2B-PARO

Run Hermes

hermes

liang2kl commited on Mar 13

Commit

c931afe

verified ·

1 Parent(s): c956635

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +16 -2

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ base_model:
 ParoQuant is the state-of-the-art INT4 quantization for LLMs. It closes the accuracy gap with FP16 while running at near-AWQ speed. Supports NVIDIA GPUs (vLLM, Transformers) and Apple Silicon (MLX).
-[`z-lab/Qwen3.5-2B-PARO`](https://huggingface.co/z-lab/Qwen3.5-2B-PARO) is a 4-bit [`Qwen/Qwen3.5-2B`](https://huggingface.co/Qwen/Qwen3.5-2B) quantized with [ParoQuant](https://github.com/z-lab/paroquant). Check out other ParoQuant models from the Hugging Face [collection](https://huggingface.co/collections/z-lab/paroquant). Swap the model name in the commands below to try any of them.
 ## Quick Start
@@ -27,9 +27,14 @@ ParoQuant is the state-of-the-art INT4 quantization for LLMs. It closes the accu
 ### Installation
 ```bash
-# NVIDIA GPU
 pip install "paroquant[vllm]"
 # Apple Silicon
 pip install "paroquant[mlx]"
 ```
@@ -40,12 +45,16 @@ pip install "paroquant[mlx]"
 python -m paroquant.cli.chat --model z-lab/Qwen3.5-2B-PARO
 ```
 ### OpenAI-Compatible API Server
 ```bash
 python -m paroquant.cli.serve --model z-lab/Qwen3.5-2B-PARO --port 8000
 ```
 ### Agent with Tool Calling
 Start the API server first, then install the agent dependencies and run:
@@ -59,13 +68,18 @@ Tool use (web fetch, filesystem, time) requires [Node.js](https://nodejs.org/en/
 ### Docker (NVIDIA GPU)
 ```bash
 # Interactive chat
 docker run --pull=always --rm -it --gpus all --ipc=host \
   ghcr.io/z-lab/paroquant:chat --model z-lab/Qwen3.5-2B-PARO
 # API server (port 8000)
 docker run --pull=always --rm -it --gpus all --ipc=host -p 8000:8000 \
   ghcr.io/z-lab/paroquant:serve --model z-lab/Qwen3.5-2B-PARO
 ```

 ParoQuant is the state-of-the-art INT4 quantization for LLMs. It closes the accuracy gap with FP16 while running at near-AWQ speed. Supports NVIDIA GPUs (vLLM, Transformers) and Apple Silicon (MLX).
+z-lab/Qwen3.5-2B-PARO is a 4-bit [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) quantized with ParoQuant. Check out other ParoQuant models from the Hugging Face [collection](https://huggingface.co/collections/z-lab/paroquant).
 ## Quick Start
 ### Installation
 ```bash
+# NVIDIA GPU (CUDA 12.9)
 pip install "paroquant[vllm]"
+# NVIDIA GPU (CUDA 13.0)
+pip install "paroquant[vllm] vllm==0.17.1" \
+  --extra-index-url https://wheels.vllm.ai/0.17.1/cu130 \
+  --extra-index-url https://download.pytorch.org/whl/cu130
 # Apple Silicon
 pip install "paroquant[mlx]"
 ```
 python -m paroquant.cli.chat --model z-lab/Qwen3.5-2B-PARO
 ```
+Add `--llm-only` if you do not wish to load the VLM components.
 ### OpenAI-Compatible API Server
 ```bash
 python -m paroquant.cli.serve --model z-lab/Qwen3.5-2B-PARO --port 8000
 ```
+Add `--llm-only` if you do not wish to load the VLM components.
 ### Agent with Tool Calling
 Start the API server first, then install the agent dependencies and run:
 ### Docker (NVIDIA GPU)
+> [!NOTE]
+> The following commands map the local cache directory to the container in order to persist kernel cache across runs. Remove `-v ...` to disable this behaviour.
 ```bash
 # Interactive chat
 docker run --pull=always --rm -it --gpus all --ipc=host \
+  -v $HOME/.cache/paroquant:/root/.cache/paroquant \
   ghcr.io/z-lab/paroquant:chat --model z-lab/Qwen3.5-2B-PARO
 # API server (port 8000)
 docker run --pull=always --rm -it --gpus all --ipc=host -p 8000:8000 \
+  -v $HOME/.cache/paroquant:/root/.cache/paroquant \
   ghcr.io/z-lab/paroquant:serve --model z-lab/Qwen3.5-2B-PARO
 ```