# Hugging Face — How to deploy and fine-tune DeepSeek models on AWS

- Company: Hugging Face (huggingface.co)
- Announced: 2025-01-30T00:00:00+00:00
- Subject: Platform
- Open weights: yes
- Models affected: DeepSeek-R1-Zero, DeepSeek-R1, deepseek-ai/DeepSeek-R1-Distill-Llama-70B, deepseek-ai/DeepSeek-R1-Distill-Qwen-32B, deepseek-ai/DeepSeek-R1-Distill-Qwen-14B, deepseek-ai/DeepSeek-R1-Distill-Llama-8B, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B, deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
- Source: https://huggingface.co/blog/deepseek-r1-aws
- Record: https://forck.live/items/1759-how-to-deploy-and-fine-tune-deepseek-models-on-aws

A guide on deploying and fine-tuning DeepSeek R1 models on AWS using Hugging Face Inference Endpoints, Amazon Bedrock Marketplace, and Amazon SageMaker AI, including code snippets and hardware recommendations for distilled variants.

## Evidence

Verbatim from https://huggingface.co/blog/deepseek-r1-aws:

> A running document to showcase how to deploy and fine-tune DeepSeek R1 models with Hugging Face on AWS.

---

Record: https://forck.live/items/1759-how-to-deploy-and-fine-tune-deepseek-models-on-aws
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md