janhq/Jan-v1-4B
Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Aug 8, 2025License:apache-2.0Architecture:Transformer0.4K Open Weights Warm

Jan-v1-4B is a 4 billion parameter agentic language model developed by janhq, based on the Qwen3-4B-thinking architecture with a 40960 token context length. It is designed for enhanced reasoning and problem-solving within the Jan App, demonstrating significant performance gains in factual question answering with 91.1% accuracy on SimpleQA. This model is optimized for complex agentic tasks and tool utilization.

Loading preview...

Jan-v1-4B: Agentic Language Model

Jan-v1-4B is the inaugural release in the Jan Family of models, developed by janhq and built upon the Qwen3-4B-thinking architecture. This 4 billion parameter model is specifically engineered for agentic reasoning and problem-solving, featuring a substantial 40960 token context length. It aims to provide enhanced capabilities for complex tasks and tool utilization, particularly within the Jan App.

Key Capabilities

  • Agentic Reasoning: Designed for advanced problem-solving and tool integration.
  • Enhanced Question Answering: Achieves 91.1% accuracy on SimpleQA, demonstrating strong factual recall and understanding.
  • Optimized for Jan App: Seamlessly integrates with the Jan App for immediate access to its features.
  • Conversational Performance: Evaluated for robust conversational and instructional capabilities through chat benchmarks.

Good For

  • Agentic Workflows: Ideal for applications requiring sophisticated reasoning and tool use.
  • Factual Question Answering: Suitable for tasks demanding high accuracy in retrieving and synthesizing information.
  • Local Deployment: Supports local inference via vLLM and llama.cpp, offering flexibility for developers.
  • Jan App Users: Provides an optimized model experience directly within the Jan App ecosystem.