Instructions to use bahadirakdemir/gemma-4-31B-it-text-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bahadirakdemir/gemma-4-31B-it-text-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="bahadirakdemir/gemma-4-31B-it-text-fp8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bahadirakdemir/gemma-4-31B-it-text-fp8")
model = AutoModelForCausalLM.from_pretrained("bahadirakdemir/gemma-4-31B-it-text-fp8", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bahadirakdemir/gemma-4-31B-it-text-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bahadirakdemir/gemma-4-31B-it-text-fp8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bahadirakdemir/gemma-4-31B-it-text-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bahadirakdemir/gemma-4-31B-it-text-fp8

SGLang

How to use bahadirakdemir/gemma-4-31B-it-text-fp8 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 "bahadirakdemir/gemma-4-31B-it-text-fp8" \
    --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": "bahadirakdemir/gemma-4-31B-it-text-fp8",
		"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 "bahadirakdemir/gemma-4-31B-it-text-fp8" \
        --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": "bahadirakdemir/gemma-4-31B-it-text-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bahadirakdemir/gemma-4-31B-it-text-fp8 with Docker Model Runner:
```
docker model run hf.co/bahadirakdemir/gemma-4-31B-it-text-fp8
```

Configuration Parsing Warning:In config.json: "num_experts" must be a number

Gemma 4 31B IT - Text-Only FP8

A text-only FP8 quantized version of google/gemma-4-31b-it.

Vision components have been removed and the remaining text model has been quantized to FP8 using NVIDIA ModelOpt with static activation calibration.

Key Details

Property	Value
Base Model	google/gemma-4-31b-it
Architecture	Gemma4ForCausalLM
Parameters	31B
Quantization	FP8 (weights + activations) via ModelOpt 0.42.0
Hidden Size	5376
Layers	60
Attention Heads	32
Context Length	262,144 tokens
Vocabulary Size	262,144

What Changed from the Base Model

Vision encoder removed - Only the text decoder (Gemma4ForCausalLM) is kept. This is not a multimodal model.
FP8 quantization applied - All Linear layers (except lm_head) are quantized to FP8 with static activation scales calibrated on 32 diverse prompts.
Smaller footprint - ~30 GB on disk vs ~62 GB for the original BF16 multimodal checkpoint.

Usage with vLLM

vllm serve bahadirakdemir/gemma-4-31B-it-text-fp8 --quantization modelopt

Usage with Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "bahadirakdemir/gemma-4-31B-it-text-fp8"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

messages = [{"role": "user", "content": "Explain FP8 quantization in two sentences."}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
inputs = inputs.to(model.device)

outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Quantization Details

Method: Post-Training Quantization (PTQ) with FP8
Tool: NVIDIA ModelOpt 0.42.0
Calibration: 32 prompts covering diverse tasks (summarization, explanation, coding, etc.)
Excluded layers: lm_head and embed_tokens remain in BF16 for output quality
Format: safetensors with quantization scales embedded in config

Files

model.safetensors - Quantized model weights (~30 GB)
config.json - Model configuration with quantization config
tokenizer.json / tokenizer_config.json - Tokenizer files
chat_template.jinja - Chat template for instruct format
generation_config.json - Default generation parameters
hf_quant_config.json - ModelOpt quantization metadata

Downloads last month: 1,035

Safetensors

Model size

31B params

Tensor type

BF16

F8_E4M3