Skip to main contentPlayground
An Open-Weight MoE LLM released under the Apache 2.0 license. It is designed for efficient, low-latency reasoning and deployment on single-GPU hardware.
Key Features
- Open-Weight: Available for unrestricted commercial and non-commercial use under the Apache 2.0 license.
- Efficient MoE: Utilizes a Mixture-of-Experts architecture for strong performance with low latency.
- On-Device Ready: Optimized for efficient deployment and inference on single-GPU hardware configurations.
