Instructions to use fcreait/Quinto-0.2-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fcreait/Quinto-0.2-9b with Transformers:

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

pipe = pipeline("image-text-to-text", model="fcreait/Quinto-0.2-9b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("fcreait/Quinto-0.2-9b")
model = AutoModelForMultimodalLM.from_pretrained("fcreait/Quinto-0.2-9b", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fcreait/Quinto-0.2-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fcreait/Quinto-0.2-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fcreait/Quinto-0.2-9b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/fcreait/Quinto-0.2-9b

SGLang

How to use fcreait/Quinto-0.2-9b 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 "fcreait/Quinto-0.2-9b" \
    --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": "fcreait/Quinto-0.2-9b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "fcreait/Quinto-0.2-9b" \
        --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": "fcreait/Quinto-0.2-9b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use fcreait/Quinto-0.2-9b with Docker Model Runner:
```
docker model run hf.co/fcreait/Quinto-0.2-9b
```

Quinto 0.2 (9B) — full weights

Full-precision weights of Quinto 0.2 (9B): Qwen/Qwen3.5-9B fine-tuned to write cleaner Italian. Training data, evaluation results and caveats are on the GGUF page.

model.safetensors-* — the base model with the LoRA merged in, stored in float16. The merge is done in float32 and saved in float16 on purpose: saving in bfloat16 rounds away a large part of the fine-tune's update.
model-mtp.safetensors — a multi-token-prediction head trained for this model (the head inside the -MTP- GGUF files), for speculative decoding.
lora/ — the LoRA adapter itself (r16, α32, checkpoint 200 of 413), for anyone who prefers to apply it to the base model.

Everything else (tokenizer, chat template, vision processor config) is the base model's.

Not identical to the GGUF files. The published GGUFs were converted from a bfloat16 merge of the same adapter, which keeps less of the update. These float16 weights are the more faithful merge, but they have not been benchmarked themselves; the numbers on the GGUF page were measured on the GGUF files.

Use

Load it as you would Qwen3.5-9B. Turn thinking off (enable_thinking: false): the fine-tune was trained and evaluated without it. The base model's recommended non-thinking sampling (temperature 0.7, top-p 0.8, top-k 20, presence penalty 1.5) is what we tested.