Trinity Large Thinking: Now available on OpenRouter.
Arcee Blog
.webp)
Company
April 14, 2026
Introducing the Trinity Builders Program
A community credit grant for developers, researchers, and open source builders working with Trinity models. Apply for free inference access on the Arcee API.](/content/blog/introducing-the-trinity-builders-program/index.html)
Agentic AI
April 3, 2026
How to Use Hermes Agent with Trinity Large Thinking
Learn how to set up Hermes Agent powered by Trinity-Large-Thinking. This guide covers installation, tool configuration, and launching your AI assistant.](/content/blog/how-to-use-hermes-agent-with-trinity-large-thinking/index.html)
.webp)
News
April 1, 2026
Trinity-Large-Thinking: Scaling an Open Source Frontier Agent
Trinity-Large-Thinking is live. A frontier open reasoning model for complex, long-horizon agents and multi-turn tool calling released under Apache 2.0.](/content/blog/trinity-large-thinking/index.html)
.webp)
News
January 27, 2026
Trinity Large
A deep dive into Trinity Large, covering architecture, sparsity, training at scale, and why we shipped Preview, Base, and TrueBase checkpoints.](/content/blog/trinity-large/index.html)
.webp)
Research
December 15, 2025
Distilling Kimi Delta Attention into AFM-4.5B (and the Tool We Used to Do It)
Learn how Kimi Delta Attention was distilled into AFM-4.5B using knowledge distillation, long-context training, and Arcee’s open-source DistillKit.](/content/blog/distilling-kimi-delta-attention-into-afm-4-5b-and-the-tool-we-used-to-do-it/index.html)
News
December 1, 2025
The Trinity Manifesto
Arcee introduces Trinity Mini, a compact MoE model trained end-to-end in the U.S., offering open weights, strong reasoning, and full control for developers.](/content/blog/the-trinity-manifesto/index.html)
.webp)
News
October 31, 2025
Mergekit Returns To Its Roots
Effective Friday, October 31, 2025, we are returning Mergekit to the GNU Lesser General Public License v3.](/content/blog/mergekit-returns-to-its-roots/index.html)
Open-Source Toolkits
October 6, 2025
IBM Research Uses Arcee MergeKit in Granite 4.0 Model Development
MergeKit helped evaluate merged checkpoints and select top performers, reflecting a broader enterprise shift to open models & reproducible tooling.](/content/blog/ibm-research-uses-arcee-mergekit-in-granite-4-0-model-development/index.html)
Research
September 30, 2025
Optimizing Arcee Foundation Models on Intel CPUs
Explore how to optimize small language models on Intel’s latest CPU, utilizing Arcee AI’s AFM-4.5B and Intel-optimized inference libraries.](/content/blog/optimizing-arcee-foundation-models-on-intel-cpus/index.html)