Llama 3.3 70B Specs, Benchmarks & Downloads
Llama 3.3 70B
Updated Llama generation
Status
active
Parameters
70.00
Context Window
131072
Modality
Text
Release Date
Dec 06, 2024
About
Explore Llama 3.3 70B, a text AI model developed by Meta. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
Llama 3.3 70B improves instruction following and reasoning capabilities.
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 model quantized
Recommended:
Use Case: Server inference
GPU Minimum: 2x RTX 4090
GPU VRAM: 48GB
System RAM: 128GB
Storage: 150GB
Operating System: Linux
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 deployment
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
|
HumanEval
|
Coding | 81.7 % | 2024 |
|
MMLU
|
Knowledge | 86.0 % | 2024 |
|
GPQA
|
Reasoning | 50.5 % | 2024 |
|
HumanEval
|
Coding | 88.4 % | 2024 |
|
MATH-500
|
Mathematics | 77.0 % | 2024 |
|
IFEval
|
Instruction Following | 92.1 % | 2024 |
Highest Benchmark
IFEval
92.1%
Benchmarks Available
6
Latest Evaluation
Dec 2024
