Llama 4 Scout 17B 16E Instruct INT4

🚀 Llama 4 Model

The Llama 4 models are natively multimodal AI models that support text and multimodal experiences. They use a mixture-of-experts architecture to achieve industry-leading performance in text and image understanding.

🚀 Quick Start

Prerequisites

Please make sure you have transformers v4.51.0 installed, or upgrade using pip install -U transformers.

Usage Example

from transformers import AutoProcessor, Llama4ForConditionalGeneration
import torch

model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"

processor = AutoProcessor.from_pretrained(model_id)
model = Llama4ForConditionalGeneration.from_pretrained(
    model_id,
    attn_implementation="flex_attention",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

url1 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
url2 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/cat_style_layout.png"
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": url1},
            {"type": "image", "url": url2},
            {"type": "text", "text": "Can you describe how these two images are similar, and how they differ?"},
        ]
    },
]

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,
)

response = processor.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])[0]
print(response)
print(outputs[0])

✨ Features

• Multimodal Capabilities: Enable text and multimodal experiences, supporting both text and image understanding.
• Mixture-of-Experts Architecture: Offer industry-leading performance in text and image understanding.
• Two Efficient Models: Launch Llama 4 Scout (17B params, 16 experts) and Llama 4 Maverick (17B params, 128 experts).

📦 Installation

To use the model with the transformers library, ensure you have transformers v4.51.0 installed. You can upgrade it using the following command:

pip install -U transformers

💻 Usage Examples

Basic Usage

from transformers import AutoProcessor, Llama4ForConditionalGeneration
import torch

model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"

processor = AutoProcessor.from_pretrained(model_id)
model = Llama4ForConditionalGeneration.from_pretrained(
    model_id,
    attn_implementation="flex_attention",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

url1 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
url2 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/cat_style_layout.png"
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": url1},
            {"type": "image", "url": url2},
            {"type": "text", "text": "Can you describe how these two images are similar, and how they differ?"},
        ]
    },
]

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,
)

response = processor.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])[0]
print(response)
print(outputs[0])

📚 Documentation

Model Information

• Model developer: Meta
• Model Architecture: The Llama 4 models are auto-regressive language models that use a mixture-of-experts (MoE) architecture and incorporate early fusion for native multimodality.

• Supported languages: Arabic, English, French, German, Hindi, Indonesian, Italian, Portuguese, Spanish, Tagalog, Thai, and Vietnamese.
• Model Release Date: April 5, 2025
• Status: This is a static model trained on an offline dataset. Future versions of the tuned models may be released as we improve model behavior with community feedback.
• License: A custom commercial license, the Llama 4 Community License Agreement, is available at: https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE
• Where to send questions or comments about the model: Instructions on how to provide feedback or comments on the model can be found in the Llama README. For more technical information about generation parameters and recipes for how to use Llama 4 in applications, please go here.

Intended Use

• Intended Use Cases: Llama 4 is intended for commercial and research use in multiple languages. Instruction tuned models are intended for assistant-like chat and visual reasoning tasks, whereas pretrained models can be adapted for natural language generation. For vision, Llama 4 models are also optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. The Llama 4 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 4 Community License allows for these use cases.
• Out-of-scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 4 Community License. Use in languages or capabilities beyond those explicitly referenced as supported in this model card.

⚠️ Important Note

1. Llama 4 has been trained on a broader collection of languages than the 12 supported languages (pre-training includes 200 total languages). Developers may fine-tune Llama 4 models for languages beyond the 12 supported languages provided they comply with the Llama 4 Community License and the Acceptable Use Policy. Developers are responsible for ensuring that their use of Llama 4 in additional languages is done in a safe and responsible manner.
2. Llama 4 has been tested for image understanding up to 5 input images. If leveraging additional image understanding capabilities beyond this, Developers are responsible for ensuring that their deployments are mitigated for risks and should perform additional testing and tuning tailored to their specific applications.

Hardware and Software

• Training Factors: We used custom training libraries, Meta's custom built GPU clusters, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
• Training Energy Use: Model pre-training utilized a cumulative of 7.38M GPU hours of computation on H100-80GB (TDP of 700W) type hardware. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
• Training Greenhouse Gas Emissions: Estimated total location-based greenhouse gas emissions were 1,999 tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with clean and renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.

The methodology used to determine training energy use and greenhouse gas emissions can be found here. Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.

Training Data

• Overview: Llama 4 Scout was pretrained on ~40 trillion tokens and Llama 4 Maverick was pretrained on ~22 trillion tokens of multimodal data from a mix of publicly available, licensed data and information from Meta’s products and services. This includes publicly shared posts from Instagram and Facebook and people’s interactions with Meta AI.
• Data Freshness: The pretraining data has a cutoff of August 2024.

Benchmarks

Pre-trained models

Instruction tuned models

^reported numbers for MMMU Pro is the average of Standard and Vision tasks

Quantization

The Llama 4 Scout model is released as BF16 weights, but can fit within a single H100 GPU with on-the-fly int4 quantization; the Llama 4 Maverick model is released as both BF16 and FP8 quantized weights. The FP8 quantized weights fit on a single H100 DGX host while still maintaining quality. We provide code for on-the-fly int4 quantization which minimizes performance loss.

🔧 Technical Details

The Llama 4 models use a mixture-of-experts (MoE) architecture and incorporate early fusion for native multimodality. This architecture allows the models to achieve industry-leading performance in text and image understanding.

📄 License

The Llama 4 models are licensed under the Llama 4 Community License Agreement. You can find the full license text at https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE.