Thinking Machines Releases Inkling-Small, Outperforms Larger Model
Thinking Machines Lab's second open-weight model needs a quarter of its predecessor's active parameters yet edges past it on reasoning and coding benchmarks.
Read more →Mixture of Experts (MoE)
Mixture of Experts (MoE) is an AI model design that holds hundreds of billions of parameters but activates only a small fraction of them for each query. This lets very large models run quickly and cheaply, and it underpins many of today’s frontier systems. This hub explains how MoE works and why it matters.
Combine with:
DeepSeek Releases V4-Flash-0731, Outperforming Its Bigger Model
DeepSeek's official V4-Flash-0731 release outperforms its larger V4-Pro model on coding and agent benchmarks, despite activating far fewer parameters per token.
Read more →Ant Group Unveils Ling-3.0-Flash, an Efficient AI Model for Agents
Ant Group's Ling-3.0-Flash matches models several times its size on reasoning and coding benchmarks using just 5.1 billion active parameters, the company says.
Read more →Moonshot AI Releases Kimi K3, Its Largest Open-Weight Model
Beijing-based Moonshot AI has published the full open weights for Kimi K3, a 2.8-trillion-parameter model it calls the largest open model released to date.
Read more →Poolside Releases Laguna S 2.1, an Open-Weight Coding Model
Poolside's new 118-billion-parameter Laguna S 2.1 matches or beats far larger rivals on agentic coding benchmarks and ships under an open license.
Read more →Moonshot AI Unveils Kimi K3, a 2.8-Trillion-Parameter Open Model
China's Moonshot AI released Kimi K3, a 2.8-trillion-parameter open model with a 1-million-token context window — a system the company calls the world's first open 3-trillion-class AI model.
Read more →What Is a Mixture of Experts (MoE) AI Model — and Why It Matters
Mixture of Experts (MoE) lets an AI model hold hundreds of billions of parameters while activating only a fraction of them per query — the main reason some huge models are also cheap to run.
Read more →