Instructions to use stamsam/Gemma_4_Gem_e4b_multimodal-NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stamsam/Gemma_4_Gem_e4b_multimodal-NF4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="stamsam/Gemma_4_Gem_e4b_multimodal-NF4")
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("stamsam/Gemma_4_Gem_e4b_multimodal-NF4")
model = AutoModelForImageTextToText.from_pretrained("stamsam/Gemma_4_Gem_e4b_multimodal-NF4")
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

vLLM

How to use stamsam/Gemma_4_Gem_e4b_multimodal-NF4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stamsam/Gemma_4_Gem_e4b_multimodal-NF4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stamsam/Gemma_4_Gem_e4b_multimodal-NF4",
		"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/stamsam/Gemma_4_Gem_e4b_multimodal-NF4

SGLang

How to use stamsam/Gemma_4_Gem_e4b_multimodal-NF4 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 "stamsam/Gemma_4_Gem_e4b_multimodal-NF4" \
    --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": "stamsam/Gemma_4_Gem_e4b_multimodal-NF4",
		"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 "stamsam/Gemma_4_Gem_e4b_multimodal-NF4" \
        --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": "stamsam/Gemma_4_Gem_e4b_multimodal-NF4",
		"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 stamsam/Gemma_4_Gem_e4b_multimodal-NF4 with Docker Model Runner:
```
docker model run hf.co/stamsam/Gemma_4_Gem_e4b_multimodal-NF4
```

Format: 4-bit NF4 | Base: google/gemma-4-E4B-it | 7.5B params

Gemma 4 Gem E4B Multimodal

A fine-tuned version of google/gemma-4-E4B-it optimized for local coding, tool use, instruction following, and structured output. Trained on an H100 via 5-stage distillation pipeline (SFT + DPO + HF curriculum augmentation).

Hard fails reduced by 76% vs stock E4B (17 → 4 on full40 benchmark).

Model Details

This model includes the original vision and audio encoders from google/gemma-4-E4B-it, allowing it to process images, audio, and text inputs. The text backbone has been fine-tuned; vision/audio encoders are from the base model.

Property	Value
Base Model	google/gemma-4-E4B-it (7.5B)
Training	5-stage CUDA pipeline (SFT → DPO → HF Curriculum)
Quantization	4-bit NF4 (bitsandbytes) — full BF16 base on request
Context	2048 tokens
Format	ChatML-style with `<

Training Datasets

stage_elite_blend (1,920 rows) — Openthoughts/Hermes/XLam gold-standard reasoning
Agentic CoT Coding SFT (429 rows) — Multi-step coding agent tasks
Glaive Function Calling v2 (1,000 rows) — Tool-use and JSON schema compliance

Benchmark Results

Comparison against stock google/gemma-4-E4B-it (4-bit):

Benchmark	Stock E4B	Gemma 4 Gem E4B	Improvement
full40	253/400 (6.33, 17 HF)	259/400 (6.47, 4 HF)	+6 pts, -13 HF
code_smoke	—	89/120 (7.42, 1 HF)	beats gate
json_hard	—	30/30 (10.0, 0 HF)	perfect
false_premise_smoke	—	87/110 (7.91, 0 HF)	clean
math_smoke	—	41/60 (6.83, 0 HF)	clean

Leaderboard Context

Model	full40	Hard Fails
Gemma 4 Gem E4B	259	4 🏆
Gemma 4 31B (cloud)	261	15
Chimera v4 (Gemma E2B)	258	14
Stock E4B (4-bit)	253	17
Granite 4.1 8B	276	14
Phi-4 Mini	223	20

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "stamsam/Gemma_4_Gem_e4b_multimodal_4-bit-NF4"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype="auto",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "Write a function to deduplicate a list"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

Hardware: NVIDIA H100 80GB SXM
Framework: PyTorch 2.11 + PEFT + bitsandbytes 4-bit QLoRA
LoRA config: r=8, alpha=16, target_modules=q/k/v/o/gate/up/down_proj
Training time: ~30 minutes total across all stages

Downloads last month: -

Safetensors

Model size

6B params

Tensor type

BF16

F32

Model tree for stamsam/Gemma_4_Gem_e4b_multimodal-NF4

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Finetuned

(182)

this model