DeepSeek-R1 7B
Parameters
7B
Context Length
131K
Modality
Text
Architecture
Dense
License
Apache 2.0
Release Date
27 Dec 2024
Knowledge Cutoff
-
API Pricing (per 1M)
Self-hosted only
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
131,072 tokens
Consumer
8x RTX 4090
24GB VRAM
Datacenter
3x NVIDIA A100
80GB VRAM
Apple Silicon
2x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#181
| Benchmark | Score | Rank |
|---|---|---|
Graduate-Level QA | 0.491 | 103 |
Rankings
Overall Rank
#181
Coding Rank
-
About DeepSeek-R1 7B
DeepSeek-R1 7B is a dense reasoning model distilled from DeepSeek-R1 onto the Qwen2.5-Math-7B foundation. It specializes in mathematical theorem proving, algorithmic problem solving, and structured logic over a 131K context window.
Technical Specifications
Attention
Attention Structure
Multi-Layer Attention
Attention Heads
64
Key-Value Heads
64
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
SwigLU
Dimensions
Hidden Dimension Size
4,096
Number of Layers
32
FFN Intermediate Size (Dense)
18,944
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
152,064
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.