XenonStudio/XenonAI-0.6B

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 18, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

XenonStudio/XenonAI-0.6B is a 0.8 billion parameter causal language model, serving as an official copy of the Qwen3-0.6B-Base model. Maintained by Xenon Studio, this model provides a foundational architecture for developing and fine-tuning custom XenonAI models. It is primarily intended as a base for further experimentation and specialized applications, rather than a pre-trained, instruction-tuned release. The model retains the Apache-2.0 license from its original Qwen Team attribution.

Loading preview...

Model Overview

XenonStudio/XenonAI-0.6B is a 0.8 billion parameter causal language model, specifically a direct copy of the Qwen/Qwen3-0.6B-Base model. This repository is maintained by Xenon Studio to provide a stable and accessible foundation for their internal XenonAI development efforts.

Key Characteristics

  • Base Model: It is the original Qwen3-0.6B-Base model, not a fine-tuned or instruction-following variant.
  • Architecture: Features a causal language model architecture with 28 layers.
  • Parameters: Contains 0.6 billion parameters, making it a compact model suitable for various applications.
  • License: Distributed under the Apache-2.0 license, inherited from the original Qwen model.

Purpose and Use Cases

This model's primary purpose is to serve as a foundational base for Xenon Studio's fine-tuning experiments and the development of their proprietary XenonAI models. Developers looking for a clean, unmodified Qwen3-0.6B-Base model to build upon will find this repository useful. It is not intended as a ready-to-use, instruction-tuned model for direct deployment in end-user applications without further fine-tuning.