#Mixture of Experts04/12/2025
Transformers vs Mixture of Experts: A Detailed Comparison
Explore the differences between Transformers and MoE models regarding performance and architecture.
FILTER MODE ACTIVE
#Mixture of Experts
Records found: 5
#Mixture of Experts12/11/2025
Baidu's ERNIE-4.5 'Thinking' Brings 3B-Scale Multimodal Reasoning
'Baidu launches ERNIE-4.5-VL-28B-A3B-Thinking, a compact open-source multimodal model that activates 3B parameters per token while offering strong document, chart and video reasoning capabilities.'
#Mixture of Experts07/11/2025
Kimi K2 Thinking: Moonshot AI's 1T-Parameter 'Thinking' Agent That Runs 200–300 Tool Calls
'Moonshot AI published Kimi K2 Thinking, a 1T-parameter Mixture of Experts thinking agent with a 256K context window and native INT4 that can perform hundreds of sequential tool calls for long-horizon tasks.'
#Mixture of Experts04/06/2025
DeepSeek-V3: Revolutionizing AI Efficiency with Hardware-Aware Design
DeepSeek-V3 introduces hardware-aware AI design innovations that dramatically improve efficiency and reduce resource requirements, enabling smaller teams to compete with tech giants.
#Mixture of Experts17/05/2025
DeepSeek-V3: Revolutionizing Language Models with Efficiency and Scalability
DeepSeek-V3 introduces innovative architecture and hardware co-design strategies that drastically improve efficiency and scalability in large language models, making high-performance AI more accessible.