Instructions to use WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4 with Transformers:

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

pipe = pipeline("text-generation", model="WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4")
model = AutoModelForCausalLM.from_pretrained("WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WaveCut/gemma-3-1b-it-qat-int4-bnb-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": "WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4

SGLang

How to use WaveCut/gemma-3-1b-it-qat-int4-bnb-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 "WaveCut/gemma-3-1b-it-qat-int4-bnb-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": "WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4",
		"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 "WaveCut/gemma-3-1b-it-qat-int4-bnb-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": "WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4 with Docker Model Runner:
```
docker model run hf.co/WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4
```

Gemma-3-1B-IT BitsAndBytesConfig NF4 Quantized

This model is a quantized version of google/gemma-3-1b-it-qat-int4-unquantized using BitsAndBytesConfig with NF4 quantization.

Model Details

Base Model: google/gemma-3-1b-it-qat-int4-unquantized
Quantization: BitsAndBytesConfig NF4 (4-bit)
Quantization Type: NF4 with double quantization
Compute Dtype: bfloat16
Storage Dtype: uint8

Quantization Configuration

from transformers import BitsAndBytesConfig

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_use_double_quant=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_quant_storage=torch.uint8
)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the quantized model
model = AutoModelForCausalLM.from_pretrained(
    "WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4",
    device_map="auto",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True
)

tokenizer = AutoTokenizer.from_pretrained("WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4")

# Generate text
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Benefits

Reduced Memory Usage: ~75% reduction in memory footprint compared to full precision
Faster Inference: Optimized for inference speed
Maintained Quality: NF4 quantization preserves model quality effectively

Hardware Requirements

GPU Memory: ~3-4GB VRAM (vs ~12GB for FP16)
CUDA Compatible: Requires CUDA-capable GPU for optimal performance
CPU Fallback: Can run on CPU with reduced performance

Quantization Details

This model uses BitsAndBytesConfig for 4-bit quantization:

NF4 (Normal Float 4) quantization for optimal quality/size trade-off
Double quantization for additional compression
Mixed precision with bfloat16 compute dtype

License

This model inherits the Apache 2.0 license from the base model.

Downloads last month: 4

Safetensors

Model size

1B params

Tensor type

F32

BF16

Model tree for WaveCut/gemma-3-1b-it-qat-int4-bnb-nf4

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Finetuned

google/gemma-3-1b-it-qat-int4-unquantized

Quantized

(4)

this model