Llama 3 70B Specs, Benchmarks & Downloads
Llama 3 70B
Meta high capability model
Status
active
Parameters
70.00
Context Window
8192
Modality
Text
Release Date
Apr 18, 2024
About
Explore Llama 3 70B, a text AI model developed by Meta. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
Llama 3 70B provides advanced general language performance for open deployment.
Family
LlamaDeveloper
MetaArchitecture
Decoder OnlyLicense
Llama Community LicenseHardware Requirements
Minimum:
Use Case: Local inference
GPU Minimum: RTX 4090
GPU VRAM: 24GB
System RAM: 64GB
Storage: 100GB
Operating System: Linux
70B quantized model
Recommended:
Use Case: Multi GPU inference
GPU Minimum: 2x RTX 4090
GPU VRAM: 48GB
System RAM: 128GB
Storage: 150GB
Operating System: Linux
Recommended multi GPU setup
High Performance:
Use Case: Production serving
GPU Minimum: 4x A100
GPU VRAM: 320GB
System RAM: 256GB
Storage: 250GB
Operating System: Linux
Enterprise serving
Model Deployment Readiness
Model Ecosystem Support
24%
Platforms
50%
Features
2%
Downloads
20%
Platform Compatibility
50%
Supported across 6 of 12 platforms
Context Window
Industry-standard context window comparison
8,192
tokens
8K
4K
32K
128K
1M
2M
Database Rank
#55
Percentile
Top 46%
Capacity
Medium
Benchmark Performance
Evaluation profile across publicly reported benchmarks
|
MMLU
|
Knowledge | 82.0 % | 2024 |
|
GPQA
|
Reasoning | 39.5 % | 2024 |
|
HumanEval
|
Coding | 81.7 % | 2024 |
|
GSM8K
|
Mathematics | 93.0 % | 2024 |
|
MATH-500
|
Mathematics | 50.4 % | 2024 |
Highest Benchmark
GSM8K
93.0%
Benchmarks Available
5
Latest Evaluation
Apr 2024
