AITOPAI热报
ModelsOfficial72°

Kimi K3 正式开源：Moonshot AI 发布 2.8T 参数 MoE 模型及基础设施

Kimi K3 Officially Open-Sourced: Moonshot AI Releases 2.8 Trillion Parameter Model Weights, Technical Report, and Three Infrastructure Technologies

Primary sourcepandaily@[email protected] (Pandaily)
Blog/Media· 11 sources
Read the original
Why we picked it

Moonshot AI 发布了 2.8T 参数的 Kimi K3，MoE 架构加 1M 上下文，还配套了工具，开源党可以玩起来了。

Moonshot AI 正式开源 Kimi K3 模型，拥有 2.8T MoE 参数、896 个路由专家，每 token 激活 16 个专家，支持 1M 上下文窗口。

Body

同时开源 MoonEP、FlashKDA 和 AgentEnv 三项基础设施技术。技术报告与模型权重同步发布。

Original · pandaily

Kimi K3 Officially Open-Sourced: Moonshot AI Releases 2.8 Trillion Parameter Model Weights, Technical Report, and Three Infrastructure Technologies

Moonshot AI open-sources Kimi K3 with 2.8T MoE parameters, 896 routed experts, 16 active per token, 1M context window, plus MoonEP, FlashKDA, and AgentEnv infrastructure tools.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Kimi K3, Moonshot AI, MoE, 开源模型.

Primary source verification: published directly by pandaily with first-party authority. Cross-source corroboration: 11 independent sources have covered this development (including SuperTechFans, The Rundown AI, 宝玉), confirming industry-wide signal strength.

#Kimi K3#Moonshot AI#MoE#开源模型#1M上下文

Keep reading

Recent stories with the same tag or section
How-toBuilders15:35
Chinese content网友用停产傲腾内存无显卡跑通 Kimi K3，每秒输出 1.5 词元

这个折腾太硬核了：一块显卡都没有，靠停产的傲腾内存加至强 CPU 跑通月之暗面那个 2.8 万亿参数的 Kimi K3，用 llama.cpp 推理，1 比特量化最快每秒 1.5 个词元。速度感人但证明了家用硬件也能啃超大模型，对喜欢搞本地部署的玩家很有参考价值。

#Kimi K3#llama.cpp#Intel Optane#月之暗面
Event
IT之家Source
PapersBuildersMulti-source10:59
Chinese contentEvoX 论文提出把 Agent Harness 视作运行时策略

一篇关于 agent 工程的硬核论文：EvoX 用 Rust 写的运行时层去管住模型落地时的工具调用、中断恢复和结果校验，不靠记忆和插件就拿到 691 组测试里 56.2% 的成功率。做 agent 框架或工程化落地的开发者建议看看它对 GLM-5.3 和 Kimi K3 提升最大的原因。

#EvoX#agent#论文#GLM-5.3
Event
arXiv cs.AI@Haoyang Zhang et al. (6)Source
PapersUS vs ChinaOfficial10:35
Chinese content姚期智与杨植麟联合发布 TCSExam 基准，Kimi K3 刷新图论纪录

姚期智和杨植麟一起做了个理论计算机科学基准，用 Lean 4 自动判分，Kimi K3 还顺手刷了个 124 顶点 630 边的图论纪录。做形式化验证或模型评测的人可以看看它的出题思路。

#TCSExam#Kimi K3#Lean 4#推理模型
Event
Primary sourcepandaily@[email protected] (Pandaily)Source
PapersBuildersMulti-sourceSelected10:28
Together Compiler Hits 2.6x Speedups on Frontier Model Inference

An agent loop that continuously recompiles inference engines against live traffic could shift how serving providers keep pace with rapidly changing model architectures, replacing static hand-tuned kernels. Teams running inference infrastructure or building MoE serving stacks can study the tiered persistent engine design and context-management ablations for their own optimizer setups. The results also benchmark directly against open source engines on Chinese frontier models like DeepSeek v4.1 Flash and Kimi K3, a useful comparison point when evaluating serving providers.

#Together AI#DeepSeek#Kimi#inference optimization
Event
arXiv: DeepSeek@Reyna Abhyankar et al. (12)Source
ProductsUS vs ChinaMulti-sourceSelected01:12
Together Compiler Hits 2.7× Throughput Gain on B200 and B300

The gap between 1.5× and 2.7× across models suggests the compiler's optimizations are architecture-dependent, so teams should benchmark their specific model before committing. Teams self-hosting or choosing an inference provider for Kimi, GLM, DeepSeek, or MiniMax models can use these figures to compare serving costs. Together's pitch targets the growing ecosystem serving Chinese open-weight models on NVIDIA's B-series hardware.

#Together AI#Kimi K3#DeepSeek#inference optimization
Event
Official accountTogether AI@togethercomputeSource