A general purpose multimodal, multilingual 128 MoE model with 17B parameters.
Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.
Powerful, multimodal language model designed for enterprise applications, including software development, data analysis, and reasoning.
Updated version of DeepSeek-R1 with enhanced reasoning, coding, math, and reduced hallucination.
Advanced reasoing MOE mode excelling at reasoning, multilingual tasks, and instruction following
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
A multimodal, multilingual 16 MoE model with 17B parameters.
Leading reasoning and agentic AI accuracy model for PC and edge.
Cutting-edge open multimodal model exceling in high-quality reasoning from images.
Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.
Generalist model to generate future world state as videos from text and image prompts to create synthetic training data for robots and autonomous vehicles.