zenlm/zen-nano

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 26, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Warm

zenlm/zen-nano is a compact 0.6 billion parameter language model, repackaged from Alibaba Qwen's Qwen3-0.6B architecture. Designed for fast inference and edge deployment, this model provides a permissively-licensed redistribution within the OSS-clean Zen model line. Its primary strength lies in its small size, making it suitable for resource-constrained environments.

Loading preview...

zen-nano: Compact Model for Edge Deployment

zenlm/zen-nano is a compact language model optimized for efficient inference and deployment in resource-constrained environments, such as edge devices. It is a repackaged version of the Qwen/Qwen3-0.6B model developed by Alibaba Qwen, maintaining its apache-2.0 license.

Key Capabilities

  • Compact Size: Features 0.6 billion dense parameters, enabling faster processing and reduced memory footprint compared to larger models.
  • Efficient Inference: Specifically designed for scenarios where rapid response times are critical.
  • Edge Deployment: Suitable for integration into applications running on devices with limited computational resources.
  • Permissively Licensed: Distributed under the Apache 2.0 license, facilitating broad use and integration into open-source projects.

Good For

  • Resource-constrained applications: Ideal for use cases where computational power or memory is limited.
  • Fast inference scenarios: When quick responses are a priority.
  • Edge computing: Deploying language model capabilities directly on user devices or IoT hardware.
  • Developers seeking OSS-clean models: Provides a permissively licensed base for further development and integration.