DeepSeek VL 7B Specs, Benchmarks & Downloads
DeepSeek VL 7B
Vision language model
Status
active
Parameters
7.00
Context Window
4096
Modality
Vision
Release Date
Mar 11, 2024
About
Explore DeepSeek VL 7B, a vision AI model developed by . View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
DeepSeek VL combines visual understanding with language reasoning.
Family
DolphinDeveloper
N/AArchitecture
TransformerLicense
Llama Community LicenseHardware Requirements
Minimum:
Use Case: Vision inference
GPU Minimum: RTX 3060
GPU VRAM: 12GB
System RAM: 32GB
Storage: 60GB
Operating System: Linux
DeepSeek VL 7B deployment
Recommended:
Use Case: Multimodal inference
GPU Minimum: RTX 4090
GPU VRAM: 24GB
System RAM: 64GB
Storage: 80GB
Operating System: Linux
Recommended vision deployment
High Performance:
Use Case: Vision serving
GPU Minimum: 2x RTX 4090
GPU VRAM: 48GB
System RAM: 128GB
Storage: 150GB
Operating System: Linux
High throughput multimodal
Model Deployment Readiness
Model Ecosystem Support
15%
Platforms
25%
Features
1%
Downloads
20%
Platform Compatibility
25%
Supported across 3 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
|
MMMU
|
Vision | 53.0 % | 2024 |
|
MMLU
|
Knowledge | 36.5 % | 2024 |
Highest Benchmark
MMMU
53.0%
Benchmarks Available
2
Latest Evaluation
Mar 2024
