The Trinity Manifesto

Arcee AI | Arcee Debuts Trinity Mini, Expanding Its U.S.-Built Model Line

Trinity Large Thinking: Available on OpenRouter.

Try now ↗

ENTERPRISE

Research

COMPANY

Get API

Blog / The Trinity Manifesto

The Trinity Manifesto Lucas Atkins ,

•

December 1, 2025

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.

Over the last year, anyone who cares about open weight language models has been watching Chinese labs. Qwen, DeepSeek and others now define a lot of what "state of the art open MoE" looks like. In the United States, most of the action has centered on polishing other people's checkpoints. At Arcee AI we want to add something that has been missing in that picture: a serious open weight model family trained end to end in America, by an American company, with weights that businesses and developers can actually own. That family is Trinity. Trinity Nano and Trinity Mini are available now. Trinity Large is currently training on 2048 B300 GPUs and will arrive in January 2026. Trinity Mini is our fully post-trained reasoning model. Trinity Nano Preview is something different: a personality-forward chat model that pushes the limits of sparsity with only 800M non-embedding parameters active per token across 56 layers and 128 experts. It's charming, it's fun to talk to, and it may be unstable in edge cases. This is an experimental release, not a thinking model. Nano Preview is available to download from Hugging Face but won't be hosted on our API. This is the story of why we decided to go all in on pretraining, how Nano and Mini came to life, and where Trinity is headed next. Why we decided to own pretraining For a while, our strategy looked like everyone else's. Take a strong open base, post train it hard, wire it into tools and RAG, and ship. That approach carried us very far. You can get impressive behavior with a good base, careful data and an instruction stack that matches the product. At the same time, a few pressures kept building: Ceilings on certain workloads: On some high stakes use cases, we kept iterating on post training and could see clear diminishing returns. Failure patterns pointed back to missing capabilities in the foundation, not to tuning mistakes. Jurisdictional Safety: Enterprise buyers are increasingly asking where the base model came from, what data went into it, and which licenses govern it. "We fine tuned a model with unknown data provenance" does not satisfy compliance officers. An end-to-end US data pipe offers legal certainty that foreign black-box models cannot. Long term product vision: We strongly believe that within two years, all meaningful AI applications will look like systems that grow and learn inside the environments where their users interact with them. Those systems will adapt their own training loops, and build and train directly from live usage. To build that kind of software you need to control the weights and the training pipeline, not only the instruction layer.

We still use and appreciate great open-source models from others. We just came to the conclusion that if we want to offer truly long-lived, self-improving systems to customers, we also need to train our own foundations. AFM 4.5B: proving we could do this Our first step was AFM-4.5B, a dense 4.5B model trained on about 8 trillion curated tokens in partnership with DatologyAI. AFM-4.5B was our "can we do this at all" experiment: Stand up large-scale data (with DatologyAI) and training pipelines. Validate that careful and considered data curation gives clean scaling behavior. Get real experience with training end-to-end.

It worked. AFM-4.5B gave us a solid base of training and infrastructure practices, and showed us where to focus on capability improvements, especially around math and code. Those lessons feed directly into Trinity. From AFM to Trinity Nano and Mini Trinity is our open weight MoE family. We chose to leap directly toward the frontier and then worked backward from that goal, which meant designing Nano and Mini as the two form factors that could both serve real users today and teach us how to train something far larger. Trinity Nano Preview: 6B parameter MoE (1B active, ~800M non-embedding), 56 layers, 128 experts with 8 active per token Trinity Mini: 26B parameter MoE (3B active), fully post-trained reasoning model

Both are released under Apache 2.0 . Download Nano Preview and Mini from Hugging Face . Mini is also available through our API and OpenRouter. Nano Preview is download-only. Originally we thought of Nano and Mini strictly as training wheels for Trinity Large. The plan was to iron out our MoE recipe, then move on. In practice, the models proved stronger than expected and now serve different roles: Mini is a compact reasoning model designed for agents, tools, and other multi-step workloads. Its output quality sits close to current instruct models. Nano Preview is an experimental model tuned for low-resource chat and instruction-following tasks. It is optimized for small deployments and will graduate from preview when Trinity-Large is released. They are some of the most cost efficient models in the world, with API pricing of $0.045 / $0.15 for the Trinity-Mini model, plus a free tier with rate limits to back that up. Both models anchor a preview of our own chat and API platform at chat.arcee.ai , which will also host Trinity Large.

The Trinity architecture Building on our AFM naming convention, we refer to this Trinity architecture as afmoe , which integrates leading global architectural advances such as gated attention and Muon within a clean, US-controlled data pipeline. Here is what the stack looks like. Attention The attention mechanism combines several techniques that have proven effective at scale. We use grouped-query attention, mapping multiple query heads to each key-value head to reduce memory bandwidth during inference. Before computing scaled dot-product attention, we apply RMSNorm to the queries and keys (QK-norm), which stabilizes training. We also use gated attention, specifically the G1 configuration from the Qwen paper. After SDPA, the output is elementwise-gated before the output projection: out_proj(sdpa_out * \\sigma(gate_proj(x))) . This gives the model a learned ability to modulate attention outputs per-position. Finally, we adopt a local/global attention pattern at a 3:1 ratio. Three local attention...