Trinity-Nano (6B)

Overview

Trinity Nano is a 6B-parameter (1B active) sparse mixture-of-experts language model, optimized for high-efficiency inference in real-time, on-device, and embedded AI applications.

Key Features

• Efficient attention mechanism: reduces memory and compute requirements while preserving long-context coherence.

• 128K-token context window: supports multi-turn interactions and extended document processing.

• Strong context utilization: fully leverages long inputs for coherent multi-turn reasoning and reliable function/tool calls.

• High inference efficiency: generates tokens rapidly while minimizing compute, delivering an outstanding price-to-performance ratio.

Deployment Quickstart

To get started deploying Trinity-6B, download the model here and proceed to Quick Deploys

Model Summary

Name	Trinity-Nano-6B
Architecture	Mixture-of-Experts
Parameters	6 Billion Total, 1 Billion Active
Experts	128 Experts, 8 Active
Attention Mechanism	Grouped Query Attention (GQA)
Training Tokens	10 trillion
License	Apache 2.0
Recommended Inference Parameters	temperature: 0.15 top_p: 0.75 top_k: 50 min_p: 0.06