Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified50% confidenceFactExact time

MoE 架构自2022年前后在大语言模型领域广泛普及，Mixtral、DeepSeek-V2、MiniMax M3均是典型实践者

1

Sources

50%

Confidence

Long-term

Relevance

7/21/2026

First Seen

Sources

MiniMax M3本地部署：激活参数23B≠显存23B，MoE架构全解析

Related Claims

UnverifiedDeepSeek-V2 was released in May 2024 and uses MoE (Mixture of Experts) architecture.64% similar UnverifiedPrompt Engineering的兴起与2022-2023年大语言模型（LLM）的爆发密切相关62% similar Unverified2024年开源社区的LLaMA 3、Qwen 2、DeepSeek等模型持续刷新性能基准62% similar Verified豆包是字节跳动于2023年推出的大语言模型系列，基于其自研的云雀（Skylark）模型架构迭代演进61% similar Unverified2023年后大语言模型迭代催生了Cursor、Bolt等专为AI编程设计的工具60% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/577412

API

curl https://kongchang.com/api/v1/knowledge/claims/577412

MCP

get_claim(id=577412)