DeepSeek-V3.2
Active Parameters
671B
Context Length
128K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
MIT
Release Date
10 Jan 2026
Knowledge Cutoff
-
Technical Specifications
Total Expert Parameters
37.0B
Number of Experts
-
Active Experts
-
Attention Structure
Multi-Head Attention
Hidden Dimension Size
-
Number of Layers
-
Attention Heads
-
Key-Value Heads
-
Activation Function
-
Normalization
-
Position Embedding
Absolute Position Embedding
System Requirements
VRAM requirements for different quantization methods and context sizes
DeepSeek-V3.2
DeepSeek-V3.2 is a powerful open-source Mixture-of-Experts (MoE) language model with 671B total parameters and 37B activated parameters per token. Built with an innovative architecture combining Multi-head Latent Attention (MLA) and DeepSeekMoE for efficient inference. Achieves exceptional performance across multiple benchmarks: 90.2% on MMLU-Pro, 84.5% on GPQA Diamond, 91.6% on MATH-500, 78.1% on Codeforces, and 92.3% on HumanEval. Supports 128k context window with strong multilingual capabilities. Features superior coding abilities, advanced mathematical reasoning, and competitive performance with leading closed-source models. Trained on 14.8 trillion diverse, high-quality tokens. MIT licensed for both research and commercial use. Ideal for complex reasoning, code generation, mathematical problem-solving, and general-purpose language understanding tasks.
About DeepSeek-V3
DeepSeek-V3 is a Mixture-of-Experts (MoE) language model comprising 671B parameters with 37B activated per token. Its architecture incorporates Multi-head Latent Attention and DeepSeekMoE for efficient inference and training. Innovations include an auxiliary-loss-free load balancing strategy and a multi-token prediction objective, trained on 14.8T tokens.
Other DeepSeek-V3 Models
Evaluation Benchmarks
Rank
#38
| Benchmark | Score | Rank |
|---|---|---|
Coding Aider Coding | 0.74 | 7 |
Agentic Coding LiveBench Agentic | 0.47 | 14 |
Coding LiveBench Coding | 0.76 | 15 |
Data Analysis LiveBench Data Analysis | 0.67 | 34 |
Reasoning LiveBench Reasoning | 0.46 | 37 |
Mathematics LiveBench Mathematics | 0.64 | 40 |
Graduate-Level QA GPQA | 0.8 | 50 |
Rankings
Overall Rank
#38
Coding Rank
#12
GPU Requirements
Full Calculator
Choose the quantization method for model weights
Context Size: 1,024 tokens