Llama 3.2 Vision 90B Specs, Benchmarks & Downloads
Llama 3.2 Vision 90B
Larger vision language model
Status
active
Parameters
90.00
Context Window
131072
Modality
Vision
Release Date
Sep 25, 2024
About
Explore Llama 3.2 Vision 90B, a vision AI model developed by Meta. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
Llama 3.2 Vision 90B provides advanced multimodal capabilities.
Family
LlamaDeveloper
MetaArchitecture
Vision Language ModelLicense
Llama Community LicenseHardware Requirements
Minimum:
Use Case: Vision inference
GPU Minimum: 2x RTX 4090
GPU VRAM: 48GB
System RAM: 128GB
Storage: 150GB
Operating System: Linux
90B vision model
Recommended:
Use Case: Server inference
GPU Minimum: 4x A100
GPU VRAM: 320GB
System RAM: 256GB
Storage: 300GB
Operating System: Linux
Large multimodal deployment
High Performance:
Use Case: Enterprise vision serving
GPU Minimum: 8x H100
GPU VRAM: 640GB
System RAM: 512GB
Storage: 500GB
Operating System: Linux
Maximum throughput
Model Deployment Readiness
Model Ecosystem Support
18%
Platforms
33%
Features
1%
Downloads
20%
Platform Compatibility
33%
Supported across 4 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
|
MMMU
|
Vision | 54.7 % | 2024 |
|
MMLU
|
Knowledge | 78.0 % | 2024 |
Highest Benchmark
MMLU
78.0%
Benchmarks Available
2
Latest Evaluation
Sep 2024
