Llama 3 8B Specs, Benchmarks & Downloads
Llama 3 8B
Meta next generation model
Status
active
Parameters
8.00
Context Window
8192
Modality
Text
Release Date
Apr 18, 2024
About
Explore Llama 3 8B, a text AI model developed by Meta. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
Llama 3 8B improved instruction following reasoning and coding performance.
Family
LlamaDeveloper
MetaArchitecture
Decoder OnlyLicense
Llama Community LicenseHardware Requirements
Minimum:
Use Case: Local inference
GPU Minimum: RTX 3060
GPU VRAM: 12GB
System RAM: 16GB
Storage: 30GB
Operating System: Windows Linux macOS
8B model deployment
Recommended:
Use Case: Desktop inference
GPU Minimum: RTX 4070
GPU VRAM: 12GB
System RAM: 32GB
Storage: 40GB
Operating System: Linux
Balanced local performance
High Performance:
Use Case: High throughput inference
GPU Minimum: RTX 4090
GPU VRAM: 24GB
System RAM: 64GB
Storage: 50GB
Operating System: Linux
Fast generation speed
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 | 68.4 % | 2024 |
|
GPQA
|
Reasoning | 34.2 % | 2024 |
|
HumanEval
|
Coding | 62.2 % | 2024 |
|
GSM8K
|
Mathematics | 79.6 % | 2024 |
|
MATH-500
|
Mathematics | 30.5 % | 2024 |
Highest Benchmark
GSM8K
79.6%
Benchmarks Available
5
Latest Evaluation
Apr 2024
