Exciting news, developers: DeepSeek is now available on AWS.
The model has made serious waves in AI, disrupting competitors like ChatGPT with cutting-edge natural language processing (NLP) and code generation.
And now, you can tap into all that power...without dealing with infrastructure headaches.
So whether you’re a developer looking to supercharge applications with real-time AI, a data scientist fine-tuning models for advanced analytics, or a business leader leveraging AI for automation and deeper insights—AWS makes it effortless to integrate DeepSeek at scale.
In this newsletter, we’ll cover:
How to get started with DeepSeek on AWS
Where to access DeepSeek models on AWS
Resources to master GenAI on AWS
Best practices for deploying DeepSeek efficiently
Let's dive in.
DeepSeek offers a range of distilled models optimized for efficiency and performance, making them well-suited for various AI applications.
These models leverage knowledge distillation, where a smaller model learns from a larger one, retaining strong capabilities while reducing computational costs.
Whether you need a lightweight model for resource-constrained environments or a high-performance model for complex reasoning tasks, DeepSeek provides multiple options tailored to different needs.
Here are the DeepSeek models available on AWS:
Model Name | Base Architecture | Parameter Count | Features |
DeepSeek-R1-Distill-Qwen-7B | Qwen | 7 billion | Balanced performance and efficiency for general applications |
DeepSeek-R1-Distill-Qwen-32B | Qwen | 32 billion | Outperforms OpenAI’s o1-mini across various benchmarks, achieving new state-of-the-art results |
DeepSeek-R1-Distill-Qwen-14B | Qwen | 14 billion | Enhanced reasoning capabilities with moderate computational requirements |
DeepSeek-R1-Distill-Qwen-1.5B | Qwen | 1.5 billion | Compact model suitable for resource-constrained environments |
DeepSeek-R1-Distill-Llama-8B | Llama | 8 billion | Efficient model with a focus on reasoning tasks |
DeepSeek-R1-Distill-Llama-70B | Llama | 70 billion | High-performance model designed for complex reasoning and instruction-based tasks |
These models are available in the “US East (Ohio)” and “US West (Oregon)” regions on AWS.
Now that we know which models are available and what they are capable of, let’s see how we access these models in our AWS environment.