Llama 3.1 405B Specs, Benchmarks & Downloads
Llama 3.1 405B
Flagship Llama model
Status
active
Parameters
405.00
Context Window
131072
Modality
Text
Release Date
Jul 23, 2024
About
Explore Llama 3.1 405B, a text AI model developed by Meta. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
Llama 3.1 405B is Meta's largest open-weight language model.
Family
LlamaDeveloper
MetaArchitecture
Decoder OnlyLicense
Llama Community LicenseHardware Requirements
Minimum:
Use Case: Distributed inference
GPU Minimum: 8x RTX 4090
GPU VRAM: 192GB
System RAM: 256GB
Storage: 500GB
Operating System: Linux
405B requires distributed setup
Recommended:
Use Case: Server inference
GPU Minimum: 8x A100
GPU VRAM: 640GB
System RAM: 512GB
Storage: 1TB
Operating System: Linux
Large scale deployment
High Performance:
Use Case: Enterprise inference
GPU Minimum: 8x H100
GPU VRAM: 640GB
System RAM: 1024GB
Storage: 2TB
Operating System: Linux
Maximum performance configuration
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
131,072
tokens
128K
4K
32K
128K
1M
2M
Database Rank
#1
Percentile
Top 100%
Capacity
Very High
Benchmark Performance
Evaluation profile across publicly reported benchmarks
|
MMLU
|
Knowledge | 88.6 % | 2024 |
|
GPQA
|
Reasoning | 49.0 % | 2024 |
|
HumanEval
|
Coding | 89.0 % | 2024 |
|
MATH-500
|
Mathematics | 73.8 % | 2024 |
|
IFEval
|
Instruction Following | 88.6 % | 2024 |
|
MMLU
|
Knowledge | 85.2 % | 2024 |
Highest Benchmark
HumanEval
89.0%
Benchmarks Available
6
Latest Evaluation
Jul 2024
