# Models Overview

Arcee AI offers models at various sizes to meet different deployment scenarios. Choosing the right model can help you complete tasks more efficiently, accurately, and cost effectively.&#x20;

### Models

To help you find the best fit for your use case, we’ve created a table outlining the core features and strengths of each model in the Arcee AI family. Note that API hosted models are always the lastest update. Previous versions and post-trains are available for download on HuggingFace.

| Model                 | Trinity-Nano-6B                                                                                                                                                                                                                                                                                              | Trinity-Mini-26B                                                                                                                                                                                                                  | Trinity \[Coming Soon] |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- |
| **Strength**          | Lightweight, ultra-low latency model.                                                                                                                                                                                                                                                                        | Fast and cost-efficient model for well-defined tasks.                                                                                                                                                                             | Coming Soon            |
| **Ideal Deployment**  | Fully local on consumer GPUs, edge servers, and mobile devices. Tuned for offline operation.                                                                                                                                                                                                                 | Serve customer-facing apps, agent backends, and high-throughput services in your cloud or VPC.                                                                                                                                    | Coming Soon            |
| **Active Parameters** | 1B per token                                                                                                                                                                                                                                                                                                 | 3B per token                                                                                                                                                                                                                      | Coming Soon            |
| **Context Window**    | 128k tokens                                                                                                                                                                                                                                                                                                  | 128k tokens                                                                                                                                                                                                                       | Coming Soon            |
| **Reasoning Support** | Yes                                                                                                                                                                                                                                                                                                          | Yes                                                                                                                                                                                                                               | Coming Soon            |
| **Knowledge Cutoff**  | 2024                                                                                                                                                                                                                                                                                                         | 2024                                                                                                                                                                                                                              | Coming Soon            |
| **Intelligence**      | <p><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><br>Efficient</p>                                                                                                                                             | <p><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><br>Good</p> | Coming Soon            |
| **Speed**             | <p><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><br>Very Fast</p> | <p><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><br>Fast</p> | Coming Soon            |
| **Max Output Tokens** | <p>non-reasoning: 8k<br>reasoning: 32k</p>                                                                                                                                                                                                                                                                   | <p>non-reasoning: 8k<br>readoning: 32k</p>                                                                                                                                                                                        | Coming Soon            |
| **Endpoints**         | Chat Completion                                                                                                                                                                                                                                                                                              | Chat Completion                                                                                                                                                                                                                   | Coming Soon            |
