Instructions to use soyrsoyr/gemma-4-12b-it-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use soyrsoyr/gemma-4-12b-it-FP8-Dynamic with Transformers:

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

pipe = pipeline("text-generation", model="soyrsoyr/gemma-4-12b-it-FP8-Dynamic")
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("soyrsoyr/gemma-4-12b-it-FP8-Dynamic")
model = AutoModelForMultimodalLM.from_pretrained("soyrsoyr/gemma-4-12b-it-FP8-Dynamic", 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 soyrsoyr/gemma-4-12b-it-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "soyrsoyr/gemma-4-12b-it-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "soyrsoyr/gemma-4-12b-it-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/soyrsoyr/gemma-4-12b-it-FP8-Dynamic

SGLang

How to use soyrsoyr/gemma-4-12b-it-FP8-Dynamic 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 "soyrsoyr/gemma-4-12b-it-FP8-Dynamic" \
    --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": "soyrsoyr/gemma-4-12b-it-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "soyrsoyr/gemma-4-12b-it-FP8-Dynamic" \
        --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": "soyrsoyr/gemma-4-12b-it-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use soyrsoyr/gemma-4-12b-it-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/soyrsoyr/gemma-4-12b-it-FP8-Dynamic
```

Gemma 4 12B Instruct FP8 Dynamic

FP8 Dynamic quantized version of google/gemma-4-12b-it using RTN (round-to-nearest) via llm-compressor.

Model Details

Property	Value
Base Model	google/gemma-4-12b-it
Quantization Method	RTN (round-to-nearest)
Format	float-quantized (FP8)
Weight Strategy	channel (per-channel)
Activation Strategy	token (per-token, dynamic)
Weight Bits	8 (FP8 E4M3)
Model Size	~15 GB
Calibration Data	None (data-free)

Benchmark Results

Evaluated with lm-evaluation-harness v0.4.12 using vLLM v0.25.1 on 2x NVIDIA H100 80GB.

Variant	GSM8K (flexible)	GSM8K (strict)
Baseline (BF16)	87.57%	86.58%
FP8 Dynamic	87.95%	86.96%
Delta	+0.38%	+0.38%

FP8 Dynamic quantization shows no accuracy loss on GSM8K — the delta is within noise (stderr ~0.9%).

Quantization Recipe

Quantized with llm-compressor v0.12.0 on 2x NVIDIA H100 80GB GPUs.

from transformers import AutoModelForImageTextToText, AutoProcessor
from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier

MODEL_ID = "google/gemma-4-12b-it"
model = AutoModelForImageTextToText.from_pretrained(MODEL_ID, dtype="auto")

recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_DYNAMIC",
    ignore=[
        "lm_head",
        "re:.*embed_vision.*",
        "re:.*embed_audio.*",
        "re:.*vision_embedder.*",
    ],
)

oneshot(model=model, recipe=recipe)
model.save_pretrained("gemma-4-12b-it-FP8-Dynamic", save_compressed=True)

Serving with vLLM

pip install vllm
vllm serve soyrsoyr/gemma-4-12b-it-FP8-Dynamic --max-model-len 4096 --tensor-parallel-size 2

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="unused")
response = client.chat.completions.create(
    model="soyrsoyr/gemma-4-12b-it-FP8-Dynamic",
    messages=[{"role": "user", "content": "Explain quantization in one sentence."}],
    max_tokens=128,
)
print(response.choices[0].message.content)

Running on Kubernetes / OpenShift

containers:
  - name: vllm
    image: vllm/vllm-openai:latest
    args:
      - --model
      - soyrsoyr/gemma-4-12b-it-FP8-Dynamic
      - --max-model-len
      - "4096"
      - --tensor-parallel-size
      - "2"
    resources:
      limits:
        nvidia.com/gpu: "2"

Downloads last month: 36

Safetensors

Model size

13B params

Tensor type

BF16

F8_E4M3

Collection including soyrsoyr/gemma-4-12b-it-FP8-Dynamic

Gemma 4 12B Quantized

Collection

3 items • Updated 8 days ago