from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "2imi9/qwen3-1.7b-gptq-int4",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("2imi9/qwen3-1.7b-gptq-int4")

# Generate text
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Gradio Demo

python

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("2imi9/qwen3-1.7b-gptq-int4", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("2imi9/qwen3-1.7b-gptq-int4")

def chat(message, history):
    inputs = tokenizer(message, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.7)
    response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
    return response

gr.ChatInterface(chat).launch()

Perfect for Gradio demos due to small size and fast inference.

2imi9/Qwen3-1.7b-gptq-int4

Qwen3 1.7B GPTQ INT4

Model Details

Usage

Gradio Demo

2imi9/
Qwen3-1.7b-gptq-int4