Llama 4

Leading Intelligence. Unrivaled speed and efficiency.The most accessible and scalable generation of Llama is here.

LATEST

Llama 4 models

Our models are optimized for easy deployment, cost efficiency, and performance that scales to billions of users.

Llama 4 Scout

Class-leading natively multimodal model that offers superior text and visual intelligence, single H100 GPU efficiency, and a 10M context window for seamless long document analysis.

Download

Llama 4 Maverick

Industry-leading natively multimodal model for image and text understanding with groundbreaking intelligence and fast responses at a low cost.

Download

Llama 4 capabilities

Natively multimodal

Unparalleled long context

Expert image grounding

Natively Multimodal

All Llama 4 models are designed with native multimodality, leveraging early fusion that allows us to pre-train the model with large amounts of unlabeled text and vision tokens - a step change in intelligence from separate, frozen multimodal weights.

How to guides: Video capabilities

Video tutorials: Build a Multimodal WhatsApp Chatbot

Start building with Llama 4

Github

View documentation

SAFETY

Protections in the era of generative AI.

Comprehensive system-level protections proactively identify and mitigate potential risks, empowering developers to more easily deploy generative AI responsibly.

Protection tools accessible to everyone

Learn more

Llama Defenders Program

Learn more

Llama 4 benchmark

Task

Metric

Llama 4 Maverick

Llama 4 Scout

Image Reasoning

MMMU

73.4

69.4

MathVista

73.7

70.7

Image Understanding

ChartQA

88.8

DocVQA (test)

94.4

Coding

LiveCodeBench (10.01.2024 - 02.01.2025)

43.4

32.8

Reasoning & Knowledge

MMLU Pro

80.5

74.3

DocVQA (test)

69.8

57.2

Multilingual

Multilingual MMLU

84.6

Long Context

MTOB (half book)
eng->kgv/kgv->eng

54.0 / 46.4

42.2 / 36.6

MTOB (full book)
eng->kgv/kgv->eng

50.8 / 46.7

39.7 / 36.3

Methodology & Notes1. For Llama model results, we report 0 shot evaluation with temperature = 0 and no majority voting or parallel test time compute. For high-variance benchmarks (GPQA Diamond, LiveCodeBench), we average over multiple generations to reduce uncertainty.2. Specialized long context evals are not traditionally reported for generalist models, so we share internal runs to showcase llama's frontier performance.3. $0.19/Mtok (3:1 blended) is our cost estimate for Llama 4 Maverick assuming distributed inference. On a single host, we project the model can be served at $0.30 - $0.49/Mtok (3:1 blended).