Pixtral-Large-Instruct-2411-hf

Instructions to use EnlistedGhost/Pixtral-Large-Instruct-2411-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EnlistedGhost/Pixtral-Large-Instruct-2411-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="EnlistedGhost/Pixtral-Large-Instruct-2411-hf")
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("EnlistedGhost/Pixtral-Large-Instruct-2411-hf")
model = AutoModelForMultimodalLM.from_pretrained("EnlistedGhost/Pixtral-Large-Instruct-2411-hf", 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 EnlistedGhost/Pixtral-Large-Instruct-2411-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Install mistral-common:
pip install --upgrade mistral-common
# Start the vLLM server:
vllm serve "EnlistedGhost/Pixtral-Large-Instruct-2411-hf" --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EnlistedGhost/Pixtral-Large-Instruct-2411-hf",
		"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/EnlistedGhost/Pixtral-Large-Instruct-2411-hf

SGLang

How to use EnlistedGhost/Pixtral-Large-Instruct-2411-hf 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 "EnlistedGhost/Pixtral-Large-Instruct-2411-hf" \
    --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": "EnlistedGhost/Pixtral-Large-Instruct-2411-hf",
		"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 "EnlistedGhost/Pixtral-Large-Instruct-2411-hf" \
        --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": "EnlistedGhost/Pixtral-Large-Instruct-2411-hf",
		"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 EnlistedGhost/Pixtral-Large-Instruct-2411-hf with Docker Model Runner:
```
docker model run hf.co/EnlistedGhost/Pixtral-Large-Instruct-2411-hf
```

Pixtral-Large-2411-124B (Instruct)

Details:
MistralAI's Pixtral Large 2411 124B Instruct - is a frontier class full-size model based upon MistralAI's Mistral-Large-2 Although this model was initially released in November of 2024; there was never a viable version ever made public that is usable with HF (HuggingFace) Safetensors and the Safetensor libraries/system.

This release features the fully working safetensors and accompanied configuration files required to successfully use this amazing and very capable model. Don't let the "2024" initial release date fool you: this model is extremely intelligent and even when quantized to Q3_K (3-bit Quant) it absolutely is a stunning piece of work that showcases MistralAI's quality and capabilities!

Using these exact files it is possible to run this model for inference and also convert it to GGUF format using llama.cpp! Following this release (once the files are uploaded) there will be another release of the GGUF converted version which includes several Quants.

Looking for GGUF + Quant?

GGUF Converted Version: [EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF]

Updates:
(As of September 20th 2026)

All Safetensors and associated configuration files, chat-template, etc - Have Been Uploaded and Released (May this release benefit the community here at HuggingFace, Thank you MistralAI for this model!)

Attribution and Credit:

Rocketknight1 | For their amazing work at creating a HF Safetensors working data-set and files (THANK YOU!!!)
MistralAI | For creating and releasing Pixtral-Large-2411-Instruct 124B model (THANK YOU!!!)
EnlistedGhost | For updating and modifying configuration files, chat template, system prompt and uploading these changes to this release

Use and Operation: This release falls under the same usage and operation instructions and policies as the original release from MistralAI. Please refer to the original model-card and release that is linked below.

Click here to view the Original Model Card for Pixtral-Large

Legal/Terms and Licensing: This release is dictated and ruled by the same terms and conditions as well as licensing that MistralAI has imposed on the model in the same way as the original and is under all of the original model release's policies. If you have anyquestions or require additional information please refer to the original model-card and the original model release linked below!

Click here to view the Original Model Card for Pixtral-Large

Downloads last month: 65

Safetensors

Model size

124B params

Tensor type

BF16

Model tree for EnlistedGhost/Pixtral-Large-Instruct-2411-hf

Base model

mistralai/Pixtral-Large-Instruct-2411

Finetuned

(3)

this model