DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models Paper • 2401.06066 • Published Jan 11, 2024 • 65
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence Paper • 2606.19348 • Published Apr 26 • 49
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model Paper • 2405.04434 • Published May 7, 2024 • 30
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models Paper • 2512.02556 • Published Dec 2, 2025 • 274