Instructions to use unsloth/gemma-3n-E4B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/gemma-3n-E4B-it with Transformers:

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

pipe = pipeline("image-text-to-text", model="unsloth/gemma-3n-E4B-it")
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("unsloth/gemma-3n-E4B-it")
model = AutoModelForMultimodalLM.from_pretrained("unsloth/gemma-3n-E4B-it", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/gemma-3n-E4B-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/gemma-3n-E4B-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-3n-E4B-it",
		"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/unsloth/gemma-3n-E4B-it

SGLang

How to use unsloth/gemma-3n-E4B-it 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 "unsloth/gemma-3n-E4B-it" \
    --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": "unsloth/gemma-3n-E4B-it",
		"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 "unsloth/gemma-3n-E4B-it" \
        --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": "unsloth/gemma-3n-E4B-it",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use unsloth/gemma-3n-E4B-it 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 unsloth/gemma-3n-E4B-it 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 unsloth/gemma-3n-E4B-it to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/gemma-3n-E4B-it to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/gemma-3n-E4B-it",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/gemma-3n-E4B-it with Docker Model Runner:
```
docker model run hf.co/unsloth/gemma-3n-E4B-it
```

danielhanchen commited on Jul 11, 2025

Commit

45e9fb1

verified ·

1 Parent(s): 7ce786b

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

model-00001-of-00004.safetensors +2 -2
model.safetensors.index.json +3 -2

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819c6c6e757dbc63ad931336cdd62373abafaf6944973e259ae18a1790cbecca
-size 3077103576

 version https://git-lfs.github.com/spec/v1
+oid sha256:1af26e1fd61af0dc067252c907bf52900c7cd5864893e29970e6ea87320322a6
+size 3077103824

model.safetensors.index.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 8387373328,
-    "total_size": 15699956256
   },
   "weight_map": {
     "model.audio_tower.conformer.0.attention.attn.k_proj.weight": "model-00001-of-00004.safetensors",
@@ -1673,6 +1673,7 @@
     "model.vision_tower.timm_model.blocks.3.9.layer_scale.gamma": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.blocks.3.9.norm.weight": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.conv_stem.bn.weight": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.conv_stem.conv.weight": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.msfa.ffn.pw_exp.bn.weight": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.msfa.ffn.pw_exp.conv.weight": "model-00001-of-00004.safetensors",

 {
   "metadata": {
+    "total_parameters": 8387373392,
+    "total_size": 15699956384
   },
   "weight_map": {
     "model.audio_tower.conformer.0.attention.attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.blocks.3.9.layer_scale.gamma": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.blocks.3.9.norm.weight": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.conv_stem.bn.weight": "model-00001-of-00004.safetensors",
+    "model.vision_tower.timm_model.conv_stem.conv.bias": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.conv_stem.conv.weight": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.msfa.ffn.pw_exp.bn.weight": "model-00001-of-00004.safetensors",
     "model.vision_tower.timm_model.msfa.ffn.pw_exp.conv.weight": "model-00001-of-00004.safetensors",