A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026

A Round Up And Comparison of 10 Open-Weight LLM Releases in Spring 2026

This post originally appeared in Ahead of AI.

“Modeling performance is likely not attributed to the architecture design itself but rather the dataset quality and training recipes”

If you have struggled a bit to keep up with open-weight model releases this month, this article should catch you up on the main themes.

In this article, I will walk you through the ten main releases in chronological order, with a focus on the architecture similarities and differences:

1. Arcee AI’s Trinity Large (Jan 27, 2026)

2. Moonshot AI’s Kimi K2.5 (Jan 27, 2026)

3. StepFun Step 3.5 Flash (Feb 1, 2026)

4. Qwen3-Coder-Next (Feb 3, 2026)

5. z.AI’s GLM-5 (Feb 12, 2026)

6. MiniMax M2.5 (Feb 12, 2026)

7. Nanbeige 4.1 3B (Feb 13, 2026)

8. Qwen 3.5 (Feb 15, 2026)

9. Ant Group’s Ling 2.5 1T & Ring 2.5 1T (Feb 16, 2026)

10. Cohere’s Tiny Aya (Feb 17, 2026)

(PS: DeepSeek V4 will be added once released.)

Since there’s a lot of ground to cover, I will be referencing my previous The Big LLM Architecture Comparison article for certain technical topics (like Mixture-of-Experts, QK-Norm, Multi-head Latent Attention, etc.) throughout this article for background information to avoid redundancy in this article.