Instructions to use aleada/Pixtral-12B-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aleada/Pixtral-12B-W4A16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="aleada/Pixtral-12B-W4A16")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("aleada/Pixtral-12B-W4A16")
model = AutoModelForMultimodalLM.from_pretrained("aleada/Pixtral-12B-W4A16", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aleada/Pixtral-12B-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aleada/Pixtral-12B-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aleada/Pixtral-12B-W4A16",
		"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/aleada/Pixtral-12B-W4A16

SGLang

How to use aleada/Pixtral-12B-W4A16 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 "aleada/Pixtral-12B-W4A16" \
    --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": "aleada/Pixtral-12B-W4A16",
		"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 "aleada/Pixtral-12B-W4A16" \
        --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": "aleada/Pixtral-12B-W4A16",
		"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 aleada/Pixtral-12B-W4A16 with Docker Model Runner:
```
docker model run hf.co/aleada/Pixtral-12B-W4A16
```

aleada commited on Jun 30

Commit

c5ccbb3

verified ·

1 Parent(s): c72fb33

fix(card): substitute repo placeholders + drop vision note for text models

Browse files

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -67,7 +67,6 @@ docker run --runtime=nvidia --gpus all \
     -e HF_TOKEN=hf_XXX \
     vllm/vllm-openai:latest \
     --model aleada/Pixtral-12B-W4A16 \
-    --max-model-len 8192 \
     --limit-mm-per-prompt 'image=1' \
     --gpu-memory-utilization 0.92 \
     --enable-prefix-caching
@@ -75,6 +74,11 @@ docker run --runtime=nvidia --gpus all \
 vLLM auto-detects `compressed-tensors` from the model's config — no
 `--quantization` flag required (it is accepted as a redundant hint).
 Once vLLM is running, hit it with any OpenAI client:
 ```python

     -e HF_TOKEN=hf_XXX \
     vllm/vllm-openai:latest \
     --model aleada/Pixtral-12B-W4A16 \
     --limit-mm-per-prompt 'image=1' \
     --gpu-memory-utilization 0.92 \
     --enable-prefix-caching
 vLLM auto-detects `compressed-tensors` from the model's config — no
 `--quantization` flag required (it is accepted as a redundant hint).
+vLLM also picks the model's full native context window from
+`config.json` (e.g. 128k for Phi-4-mini, 16k for Phi-4 14B). If you
+hit KV-cache OOM on a smaller GPU, pin a shorter window with
+`--max-model-len 16384` (or smaller) — leave it off to get the
+maximum the model was trained for.
 Once vLLM is running, hit it with any OpenAI client:
 ```python