Llama 2 70B
Meta Released July 2023
Meta's previous generation flagship open-source model
Llama 2 70B
Meta • July 2023
Training Data
Up to early 2023
Llama 2 70B
July 2023
Parameters
70 billion
Training Method
Reinforcement Learning
Context Window
4,096 tokens
Knowledge Cutoff
September 2022
Key Features
Open Source • Commercial Use • Safety Focused
Capabilities
Reasoning: Good
Safety: Very Good
General: Good
What's New in This Version
Improved safety and helpfulness over Llama 1
Meta's previous generation flagship open-source model
What's New in This Version
Improved safety and helpfulness over Llama 1
Technical Specifications
Parameters 70 billion
Context Window 4,096 tokens
Training Method Reinforcement Learning
Knowledge Cutoff September 2022
Training Data Up to early 2023
Key Features
Open Source Commercial Use Safety Focused
Capabilities
Reasoning: Good
Safety: Very Good
General: Good
Other Meta Models
Explore more models from Meta
Llama 4 Behemoth
Meta's flagship multimodal model with massive MoE architecture (288B active parameters)
April 2025 ~2 trillion (288B active)
Llama 4 Maverick
Meta's balanced multimodal MoE model with 128 experts for general use
April 2025 400 billion (17B active)
Llama 4 Scout
Meta's efficient multimodal model with industry-leading 10M token context
April 2025 109 billion (17B active)