Llama Guard 3 1B
Meta AI's Llama Guard 3 1B is a fine-tuned chat model for content safety classification, capable of classifying both inputs and responses as safe or unsafe and listing violated content categories. It is genuinely best at safeguarding against a standardized hazards taxonomy, with a notable technical trait being its large context window of 131,072 tokens.
Input
Output
Context
131K
Max Output
131K
Parameters
1.5B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens131,072 tokens
Parameters1.5B
Release DateSep 20, 2024
Training CutoffNot available
Licensellama3.2
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Llama Guard 3 1B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.