iproskurina/gemma-3-4b-pt-gptqmodel-8bit

gemma-3-4b-pt - GPTQ (8-bit)

Source model: google/gemma-3-4b-pt

This model was quantized to 8-bit using GPTQModel.

Quantization parameters:

• bits: 8
• group_size: 128
• damp_percent: 0.05
• desc_act: False

Usage

# pip install transformers gptqmodel --no-build-isolation
from gptqmodel import GPTQModel
model_id = "iproskurina/gemma-3-4b-pt-gptqmodel-8bit"
model = GPTQModel.load(model_id)
result = model.generate("Uncovering deep insights")[0]
print(model.tokenizer.decode(result))