DeepSeek-R1-0528
DeepSeek-R1-0528 is an open-weight language model from DeepSeek, released on May 28, 2025. It is a mixture-of-experts model with 671B total parameters, of which 37B are active for each token. DeepSeek lists a context window of 128K tokens. The model takes text input.
- Developer
- DeepSeek
- Released
- May 28, 2025
- Total parameters
- 671B
- Active parameters per token
- 37B
- Architecture
- MoE
- Context window
- 128K
- Input
- Text
- License
- MIT
- Commercial use
- Yes
- Official weights, GB
- 1,369.1 GB
- Hugging Face repository
- huggingface.co
- Checked on
The weights are released under the MIT license, which allows commercial use.
The official weights on Hugging Face take about 1,369 GB. Running the model needs at least that much memory across GPUs and system RAM, plus room for the context cache; quantized versions need less.
- Total parameters, billions
- 671B
- Active parameters, billions
- 37B
- Context window, tokens
- 128K
- License type
- MIT
- License conditions
- MIT: keep the copyright and permission notice.
- Weights precision
- FP8 + BF16
- License text
- huggingface.co
- Sources
Page URL Hugging Face model card https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/raw/main/README.md Hugging Face weights index https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/raw/main/model.safetensors.index.json Hugging Face model page https://huggingface.co/deepseek-ai/DeepSeek-R1 DeepSeek API docs: release notes https://api-docs.deepseek.com/news/news250528