Open Weight Model Articles

Page 1 of 1 (4 articles)

7/28/2026 • EN

Kimi K3 Architecture Notes

Analysis of Kimi K3's open-weight architecture, focusing on LatentMoE, attention residuals, and NoPE innovations for inference efficiency.

Architecture Attention Mechanisms Kimi K3 Mixture Of Experts Open Weight Model

Sebastian Raschka

6/18/2026 • EN

GLM-5.2 and IndexShare for Long-Context Sparse Attention

Analysis of GLM-5.2, a new open-weight model with IndexShare for efficient long-context sparse attention.

Glm 52 Indexshare Long Context Open Weight Model Sparse Attention

Sebastian Raschka

6/18/2026 • EN

GLM-5.2 and IndexShare for Long-Context Sparse Attention

Analysis of GLM-5.2 open-weight model with IndexShare for efficient long-context sparse attention.

Glm 52 Indexshare Long Context Inference Open Weight Model Sparse Attention

Sebastian Raschka

6/12/2026 • EN

North Mini Code and Agentic Coding Benchmarks

Cohere's North Mini Code is a 30B-parameter open-weight model for agentic coding, featuring Mixture-of-Experts architecture and strong benchmark performance.

Agentic Coding benchmark Mixture Of Experts North Mini Code Open Weight Model

Sebastian Raschka

Open Weight Model Articles

Kimi K3 Architecture Notes

GLM-5.2 and IndexShare for Long-Context Sparse Attention

GLM-5.2 and IndexShare for Long-Context Sparse Attention

North Mini Code and Agentic Coding Benchmarks

Select Language

We use cookies