DeepSeek Coder V2 Specs, Benchmarks & Downloads
DeepSeek Coder V2
DeepSeek coding MoE model
Status
active
Parameters
236.00
Context Window
128000
Modality
Text
Release Date
Jun 17, 2024
About
Explore DeepSeek Coder V2, a text AI model developed by DeepSeek. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
DeepSeek Coder V2 uses mixture-of-experts architecture for advanced coding tasks.
Family
DeepSeekDeveloper
DeepSeekArchitecture
Mixture of ExpertsLicense
DeepSeek LicenseHardware Requirements
Minimum:
Use Case: Local inference
GPU Minimum: RTX 4090
GPU VRAM: 24GB
System RAM: 64GB
Storage: 100GB
Operating System: Linux
DeepSeek Coder V2 larger model
Recommended:
Use Case: Multi GPU inference
GPU Minimum: 2x RTX 4090
GPU VRAM: 48GB
System RAM: 128GB
Storage: 150GB
Operating System: Linux
Recommended deployment
High Performance:
Use Case: Production serving
GPU Minimum: 4x A100
GPU VRAM: 320GB
System RAM: 256GB
Storage: 300GB
Operating System: Linux
Enterprise deployment
Model Deployment Readiness
Model Ecosystem Support
12%
Platforms
17%
Features
0%
Downloads
20%
Platform Compatibility
17%
Supported across 2 of 12 platforms
Context Window
Industry-standard context window comparison
128,000
tokens
125K
4K
32K
128K
1M
2M
Database Rank
#17
Percentile
Top 84%
Capacity
High
Benchmark Performance
Evaluation profile across publicly reported benchmarks
|
HumanEval
|
Coding | 79.3 % | 2024 |
|
MMLU
|
Knowledge | 73.5 % | 2024 |
|
MATH-500
|
Mathematics | 75.0 % | 2024 |
|
SWE-Bench
|
Software Engineering | 12.7 % | 2024 |
Highest Benchmark
HumanEval
79.3%
Benchmarks Available
4
Latest Evaluation
Jun 2024
