zenlm/zen-agent-4b
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Sep 28, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Warm
The zenlm/zen-agent-4b is a compact 4 billion parameter agent model developed by Hanzo AI and the Zoo Labs Foundation. Built on the Zen MoDE (Mixture of Distilled Experts) architecture, it features a 32K context window. This model is specifically designed and optimized for strong function calling and tool-use capabilities, making it suitable for agentic workflows.
Loading preview...
Overview
zenlm/zen-agent-4b is a compact and efficient 4 billion parameter agent model, developed by Hanzo AI and the Zoo Labs Foundation. It leverages the Zen MoDE (Mixture of Distilled Experts) architecture, which contributes to its specialized performance in agentic tasks.
Key Capabilities
- Function Calling: Excels at interpreting user requests to call external functions.
- Tool-Use: Designed for robust integration and utilization of various tools within an agentic workflow.
- Compact Size: At 4 billion parameters, it offers a balance of capability and efficiency.
- Extended Context Window: Features a 32K token context window, allowing for processing longer interactions and complex instructions.
Good For
- Agentic Applications: Ideal for building AI agents that require strong function calling and tool-use abilities.
- Automated Workflows: Suitable for tasks where the model needs to interact with external systems or APIs.
- Resource-Constrained Environments: Its compact size makes it a good choice for deployments where computational resources are a consideration, without sacrificing core agentic capabilities.
This model is released under the Apache 2.0 License.