Instructions to use mlx-community/gemma-3-12b-it-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/gemma-3-12b-it-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="mlx-community/gemma-3-12b-it-4bit")
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("mlx-community/gemma-3-12b-it-4bit")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/gemma-3-12b-it-4bit")
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 mlx-community/gemma-3-12b-it-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/gemma-3-12b-it-4bit")
config = load_config("mlx-community/gemma-3-12b-it-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/gemma-3-12b-it-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/gemma-3-12b-it-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/gemma-3-12b-it-4bit",
		"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/mlx-community/gemma-3-12b-it-4bit

SGLang

How to use mlx-community/gemma-3-12b-it-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/gemma-3-12b-it-4bit" \
    --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": "mlx-community/gemma-3-12b-it-4bit",
		"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 "mlx-community/gemma-3-12b-it-4bit" \
        --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": "mlx-community/gemma-3-12b-it-4bit",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use mlx-community/gemma-3-12b-it-4bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/gemma-3-12b-it-4bit
```

prince-canuma commited on Mar 18, 2025

Commit

d896ba5

verified ·

1 Parent(s): 087be1b

Upload folder using huggingface_hub

Browse files

Files changed (6) hide show

README.md +1 -1
generation_config.json +11 -0
model-00001-of-00002.safetensors +2 -2
model-00002-of-00002.safetensors +2 -2
model.safetensors.index.json +0 -0
processor_config.json +4 -0

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ tags:
 ---
 # mlx-community/gemma-3-12b-it-4bit
-This model was converted to MLX format from [`google/gemma-3-12b-it`]() using mlx-vlm version **0.1.17**.
 Refer to the [original model card](https://huggingface.co/google/gemma-3-12b-it) for more details on the model.
 ## Use with mlx

 ---
 # mlx-community/gemma-3-12b-it-4bit
+This model was converted to MLX format from [`google/gemma-3-12b-it`]() using mlx-vlm version **0.1.18**.
 Refer to the [original model card](https://huggingface.co/google/gemma-3-12b-it) for more details on the model.
 ## Use with mlx

generation_config.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0.dev0"
+}

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3ec44aa8195b946333a3a9a7cd987a3fa695314533aa821ee00eef1f8601f7
-size 5367454243

 version https://git-lfs.github.com/spec/v1
+oid sha256:995cbd05b7bfd8f5ab5307b476eb5496b5ec3f5256a9dd26366236ce8816c93f
+size 5367455313

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f8abd76a0e2d9b008f8698812faaa2e51c22cd5afb5c257d47812e5f234819
-size 2661219601

 version https://git-lfs.github.com/spec/v1
+oid sha256:8b7af7eb5ff32109fc65cbcd0af5b8016ac0de46df17f40705f043f899495333
+size 2661219935

model.safetensors.index.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

processor_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}