Skip to main content
🦙

Llama

by Meta

5M / mo
100% Free
Try Llama (opens in a new tab)

Llama is Meta's family of open-source large language models designed for efficiency and performance. Developers deploy it on-premise or cloud for cost-effective AI inference.

Llama features and capabilities, including which plan they need and how they compare in the CanIUse matrix.

Used in combinations

See who owns what in this stack

✨ Modalities

💬
Text Input
Yes. Core feature
🖼️
Image Upload / Vision
Yes. Llama 3.2
🎨
Image Generation
No
🎙️
Voice Mode
No
🎥
Video Understanding
No
🎬
Video Generation
No. Not a video generation product.
📁
File Upload (PDF, DOCX)
No
💻
Code Execution
No
🔊
Audio Input
No
🖌️
Canvas / Artifact Editor
No
🖥️
Screen Sharing / Computer Use
No

🧠 Memory & Context

🧠
Persistent Memory
No
📏
Large Context Window
Yes. 128k tokens
⚙️
Custom Instructions
Yes
📜
Conversation History
No

🔌 Integrations

🌐
Web Search / Browsing
No
🔌
Plugins / Extensions
No
🔧
API Access
Yes. Free via API providers
⚡
Zapier Integration
No
🤖
Custom GPTs / Bots
No
👥
Real-time Collaboration
No
🐦
Live Social Data Integration
📚
Live Citation Mapping

👨‍💻 Developer

🛠️
Function Calling
Yes
⚡
Streaming Responses
Yes
🎛️
Fine-Tuning
Yes. Open weights
📐
Embeddings API
Yes
📋
Structured Output (JSON)
Yes
🧩
Reasoning / Thinking Mode
Partial. Llama 3.3 has some CoT capability
🏠
Local Execution
Yes. Weights are downloadable and run locally via llama.cpp, Ollama and similar runtimes.
🔓
Open Weights
🤖
Multi-Agent Orchestration

📱 Platforms

🌐
Web App
No
📱
iOS App
No
🤖
Android App
No
🖥️
Desktop App
No
🔵
Chrome Extension
No

🔒 Privacy

🔒
GDPR Compliant
Yes
🚫
Opt Out of Data Training
Yes
🏢
Enterprise Privacy Mode
Yes. Self-hosted

💼 Workspaces

📂
Projects / Folders
No