DeepSeek-R1 671B
Active Parameters
671B
Context Length
131K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
MIT License
Release Date
27 Dec 2024
Knowledge Cutoff
Jul 2024
API Pricing (per 1M)
Input: $2.00 · Output: $4.00
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
80x RTX 4090
24GB VRAM
Datacenter
21x NVIDIA A100
80GB VRAM
Apple Silicon
17x Apple M3 Max
128GB VRAM
131,072 tokens
Consumer
118x RTX 4090
24GB VRAM
Datacenter
29x NVIDIA A100
80GB VRAM
Apple Silicon
25x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#120
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.85 | 12 |
StackUnseen | 0.524 | 22 |
Graduate-Level QA | 0.81 | 62 |
General Text | 1422 | 91 |
Agentic Index | 0.01 | 125 |
Coding Index | 0.25 | 132 |
Intelligence Index | 0.13 | 228 |
StackEval Archived | 0.956 | 5 |
QA Assistant Archived | 0.964 | 5 |
Coding Archived | 0.71 | 7 |
Summarization Archived | 0.774 | 14 |
Rankings
Overall Rank
#120
Coding Rank
#110
About DeepSeek-R1 671B
DeepSeek-R1 is DeepSeek's flagship 671B Mixture-of-Experts reasoning model engineered with large-scale reinforcement learning for complex problem-solving. It generates explicit multi-step chains of thought for state-of-the-art math, coding, and scientific deduction.
Technical Specifications
Attention
Attention Structure
Multi-Layer Attention
Attention Heads
128
Key-Value Heads
128
Attention Head Dimension
-
Position Embedding
ROPE
RoPE Theta
10,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
Swish
Dimensions
Auxiliary Parameters
-
Hidden Dimension Size
2,048
Number of Layers
61
FFN Intermediate Size (Dense)
2,048
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
129,280
Mixture of Experts
Total Expert Parameters
37.0B
Number of Experts
64
Active Experts
6
Shared Experts
1
FFN Intermediate Size (per Expert)
2,048
Dense Layers Before MoE
3
About DeepSeek-R1
DeepSeek-R1 is a model family developed for logical reasoning tasks. It incorporates a Mixture-of-Experts architecture for computational efficiency and scalability. The family utilizes Multi-Head Latent Attention and employs reinforcement learning in its training, with some variants integrating cold-start data.