Llama 4
A new era of natively multimodal AI innovation
Developer ToolsArtificial Intelligence
Llama 4
A new era of natively multimodal AI innovation
Product upvotes vs the next 3
Product comments vs the next 3
Product upvote speed vs the next 3
Product upvotes and comments
Product vs the next 3
Llama 4
A new era of natively multimodal AI innovation
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
Top comment
The new herd of Llamas from Meta:
Llama 4 Scout:
• 17B x 16 experts
• Natively multi-modal
• 10M token context length
• Runs on a single GPU
• Highest performing small model
Llama 4 Maverick:
• 17B x 128 experts
• Natively multi-modal
• Beats GPT-4o and Gemini Flash 2
• Smaller and more efficient than DeepSeek, but still comparable on text, plus also multi-modal
• Runs on a single host
Llama 4 Behemoth:
• 2+ trillion parameters
• Highest performing base model
• Still training!