Llama 3 70B
Parameters
70B
Context Length
8K
Modality
Text
Architecture
Dense
License
Meta Llama 3 Community License
Release Date
18 Apr 2024
Knowledge Cutoff
Dec 2023
API Pricing (per 1M)
Input: $0.65 · Output: $2.75
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
7x RTX 4090
24GB VRAM
Datacenter
2x NVIDIA A100
80GB VRAM
Apple Silicon
2x Apple M3 Max
128GB VRAM
8,192 tokens
Consumer
8x RTX 4090
24GB VRAM
Datacenter
2x NVIDIA A100
80GB VRAM
Apple Silicon
2x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#161
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1276 | 137 |
Intelligence Index | 1 | 248 |
Rankings
Overall Rank
#161
Coding Rank
-
About Llama 3 70B
Llama 3 70B is a high-capacity open-weights model developed by Meta for complex reasoning, long-form summarization, and conversational AI. It is instruction-tuned for helpfulness and safety across enterprise and research environments.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
64
Key-Value Heads
8
Attention Head Dimension
-
Position Embedding
ROPE
RoPE Theta
-
Sliding Window Attention
-
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
-
Activation Function
-
Dimensions
Hidden Dimension Size
8,192
Number of Layers
80
FFN Intermediate Size (Dense)
-
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
-
About Llama 3
Meta's Llama 3 is a series of large language models utilizing a decoder-only transformer architecture. It incorporates a 128K token vocabulary and Grouped Query Attention for efficient processing. Models are trained on substantial public datasets, supporting various parameter scales and extended context lengths.