Llama 2 13B Specs, Benchmarks & Downloads
Llama 2 13B
Meta medium foundation model
Status
active
Parameters
13.00
Context Window
4096
Modality
Text
Release Date
Jul 18, 2023
About
Explore Llama 2 13B, a text AI model developed by Meta. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
Llama 2 13B provides improved reasoning and generation capability compared with smaller variants.
Family
LlamaDeveloper
MetaArchitecture
Decoder OnlyLicense
Llama Community LicenseHardware Requirements
Minimum:
Use Case: Local inference
GPU Minimum: RTX 3060
GPU VRAM: 12GB
System RAM: 32GB
Storage: 40GB
Operating System: Windows Linux macOS
13B model requires larger memory
Recommended:
Use Case: Desktop inference
GPU Minimum: RTX 3090
GPU VRAM: 24GB
System RAM: 64GB
Storage: 60GB
Operating System: Linux
Recommended quantized deployment
High Performance:
Use Case: High throughput inference
GPU Minimum: RTX 4090
GPU VRAM: 24GB
System RAM: 96GB
Storage: 80GB
Operating System: Linux
Improved throughput
Model Deployment Readiness
Model Ecosystem Support
24%
Platforms
50%
Features
1%
Downloads
20%
Platform Compatibility
50%
Supported across 6 of 12 platforms
Context Window
Industry-standard context window comparison
4,096
tokens
4K
4K
32K
128K
1M
2M
Database Rank
#72
Percentile
Top 29%
Capacity
Small
Benchmark Performance
Evaluation profile across publicly reported benchmarks
|
MMLU
|
Knowledge | 54.8 % | 2023 |
|
HumanEval
|
Coding | 18.9 % | 2023 |
Highest Benchmark
MMLU
54.8%
Benchmarks Available
2
Latest Evaluation
Jul 2023
