Echo9Zulu/

gemma-3-4b-it-qat-int4_asym-ov

import time
from PIL import Image
from transformers import AutoProcessor
from optimum.intel.openvino import OVModelForVisualCausalLM


model_id = "Echo9Zulu/gemma-3-4b-it-int8_asym-ov" # Can be an HF id or a path

ov_config = {"PERFORMANCE_HINT": "LATENCY"} # Optimizes for first token latency and locks to single CPU socket

print("Loading model... this should get faster after the first generation due to caching behavior.")
print("")
start_load_time = time.time()
model = OVModelForVisualCausalLM.from_pretrained(model_id, export=False, device="CPU", ov_config=ov_config) # For GPU use "GPU.0"
processor = AutoProcessor.from_pretrained(model_id) # Instead of using AutoTokenizers we use AutoProcessor which routes to the appropriate input processor i.e, how does a model expect image tokens.
                                                    # Under the hood this takes care of model specific preprocessing and has functionality overlap with AutoTokenizers.
end_load_time = time.time()

image_path = r"" # This script expects .png
image = Image.open(image_path)
image = image.convert("RGB") # Required by gemma3. In practice this would need to be handled at the engine level OR in model-specifc pre-processing.

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "image"
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

inputs = processor(text=[text_prompt], images=[image], padding=True, return_tensors="pt")

input_token_count = len(inputs.input_ids[0]) 
print(f"Sum of image and text tokens: {len(inputs.input_ids[0])}")

start_time = time.time()
output_ids = model.generate(**inputs, max_new_tokens=1024)

generated_ids = [output_ids[len(input_ids) :] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)

num_tokens_generated = len(generated_ids[0])
load_time = end_load_time - start_load_time
generation_time = time.time() - start_time
tokens_per_second = num_tokens_generated / generation_time
average_token_latency = generation_time / num_tokens_generated

print("\nPerformance Report:")
print("-"*50)
print(f"Input Tokens        : {input_token_count:>9}")
print(f"Generated Tokens    : {num_tokens_generated:>9}")
print(f"Model Load Time     : {load_time:>9.2f} sec")
print(f"Generation Time     : {generation_time:>9.2f} sec")
print(f"Throughput          : {tokens_per_second:>9.2f} t/s")
print(f"Avg Latency/Token   : {average_token_latency:>9.3f} sec")

print(output_text)