Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing, storytelling, role-play, chat scenarios, and real-time voice assistance. Trained to navigate well in agent harnesses like OpenCode, Cline, and Kilo Code, and to handle complex toolchains and long, constraint-filled prompts.

Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing, storytelling, role-play, chat scenarios, and real-time voice assistance. Trained to navigate well in agent harnesses like OpenCode, Cline, and Kilo Code, and to handle complex toolchains and long, constraint-filled prompts.