Instructions to use mlx-community/paligemma2-3b-pt-896-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/paligemma2-3b-pt-896-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="mlx-community/paligemma2-3b-pt-896-4bit")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mlx-community/paligemma2-3b-pt-896-4bit")
model = AutoModelForMultimodalLM.from_pretrained("mlx-community/paligemma2-3b-pt-896-4bit", device_map="auto")

MLX

How to use mlx-community/paligemma2-3b-pt-896-4bit 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("mlx-community/paligemma2-3b-pt-896-4bit")
config = load_config("mlx-community/paligemma2-3b-pt-896-4bit")

# 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

vLLM

How to use mlx-community/paligemma2-3b-pt-896-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/paligemma2-3b-pt-896-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/paligemma2-3b-pt-896-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlx-community/paligemma2-3b-pt-896-4bit

SGLang

How to use mlx-community/paligemma2-3b-pt-896-4bit 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 "mlx-community/paligemma2-3b-pt-896-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/paligemma2-3b-pt-896-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "mlx-community/paligemma2-3b-pt-896-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/paligemma2-3b-pt-896-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mlx-community/paligemma2-3b-pt-896-4bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/paligemma2-3b-pt-896-4bit
```
Atomic Chat

mlx-community/paligemma2-3b-pt-896-4bit

This model was converted to MLX format from google/paligemma2-3b-pt-896 using mlx-vlm version 0.1.4. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model mlx-community/paligemma2-3b-pt-896-4bit --max-tokens 100 --temp 0.0

Downloads last month: 57

Safetensors

Model size

3B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized