Instructions to use raazkumar/gemma-4-31B-it-mlx-2Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use raazkumar/gemma-4-31B-it-mlx-2Bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="raazkumar/gemma-4-31B-it-mlx-2Bit")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("raazkumar/gemma-4-31B-it-mlx-2Bit")
model = AutoModelForImageTextToText.from_pretrained("raazkumar/gemma-4-31B-it-mlx-2Bit")
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 raazkumar/gemma-4-31B-it-mlx-2Bit 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("raazkumar/gemma-4-31B-it-mlx-2Bit")
config = load_config("raazkumar/gemma-4-31B-it-mlx-2Bit")

# 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
LM Studio

vLLM

How to use raazkumar/gemma-4-31B-it-mlx-2Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "raazkumar/gemma-4-31B-it-mlx-2Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "raazkumar/gemma-4-31B-it-mlx-2Bit",
		"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/raazkumar/gemma-4-31B-it-mlx-2Bit

SGLang

How to use raazkumar/gemma-4-31B-it-mlx-2Bit 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 "raazkumar/gemma-4-31B-it-mlx-2Bit" \
    --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": "raazkumar/gemma-4-31B-it-mlx-2Bit",
		"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 "raazkumar/gemma-4-31B-it-mlx-2Bit" \
        --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": "raazkumar/gemma-4-31B-it-mlx-2Bit",
		"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"
						}
					}
				]
			}
		]
	}'

Pi new

How to use raazkumar/gemma-4-31B-it-mlx-2Bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "raazkumar/gemma-4-31B-it-mlx-2Bit"

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": "raazkumar/gemma-4-31B-it-mlx-2Bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use raazkumar/gemma-4-31B-it-mlx-2Bit with Docker Model Runner:
```
docker model run hf.co/raazkumar/gemma-4-31B-it-mlx-2Bit
```

raazkumar/gemma-4-31B-it-mlx-2Bit

The Model raazkumar/gemma-4-31B-it-mlx-2Bit was converted to MLX format from google/gemma-4-31B-it using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("raazkumar/gemma-4-31B-it-mlx-2Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Downloads last month: 174

Safetensors

Model size

31B params

Tensor type

BF16

U32

MLX

Hardware compatibility

2-bit

Model tree for raazkumar/gemma-4-31B-it-mlx-2Bit

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Quantized

(188)

this model