DeepSeek-R (R1)
DeepSeekChinaOpen sourceOpen weightsmittext
Reasoning models trained with RL.
Release history (12)
- DeepSeek-R1-0528-Qwen3-8BstableMay 29, 2025deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
Detected on Hugging Face Hub.
- DeepSeek-R1-0528stableMay 28, 2025deepseek-ai/DeepSeek-R1-0528
Detected on Hugging Face Hub.
- DeepSeek-R1stableJan 20, 2025deepseek-ai/DeepSeek-R1671B params
Open-weights reasoning model, MIT.
- DeepSeek-R1 (distill)stableJan 20, 2025deepseek-ai/DeepSeek-R1-Distill-Llama-70B70B params
Reasoning distillations.
- DeepSeek-R1-Distill-Qwen-7BstableJan 20, 2025deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Detected on Hugging Face Hub.
- DeepSeek-R1-Distill-Qwen-1.5BstableJan 20, 2025deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Detected on Hugging Face Hub.
- DeepSeek-R1-Distill-Qwen-32BstableJan 20, 2025deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Detected on Hugging Face Hub.
- DeepSeek-R1-Distill-Qwen-14BstableJan 20, 2025deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Detected on Hugging Face Hub.
- DeepSeek-R1-ZerostableJan 20, 2025deepseek-ai/DeepSeek-R1-Zero
Detected on Hugging Face Hub.
- DeepSeek-R1-Distill-Llama-8BstableJan 20, 2025deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Detected on Hugging Face Hub.
- DeepSeek-R1 (preview)deprecatedNov 20, 2024deepseek-ai/DeepSeek-R1-Lite-Preview671B params
Reasoning preview.
- DeepSeek-R2unconfirmed—deepseek-ai/DeepSeek-R2671B params
Next-gen reasoning. [Flagged: pre-release at time of seed; confirm before publishing.]
Spotted something out of date? Edit in admin.