license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen3-1.7B
pipeline_tag: text-generation
library_name: transformers
Jan-edge: Distilled for Edge, Built for Agents
Overview
Jan-edge is a lightweight agentic model built for fast, reliable on-device execution. As the second release in the Jan Family, it is distilled from the larger Jan-v1 model, preserving strong reasoning and problem-solving ability in a smaller footprint suitable for resource-constrained environments.
Jan-edge was developed through a two-phase post-training process. The first phase, Supervised Fine-Tuning (SFT), transferred core capabilities from the Jan-v1 teacher model to the smaller student. The second phase, Reinforcement Learning with Verifiable Rewards (RLVR) —the same method used in Jan-v1 and Lucy—further optimized reasoning efficiency, tool use, and correctness. This staged approach delivers reliable results on complex, interactive workloads.
Performance
Question Answering(SimpleQA)
Jan-edge achieves 84.2% accuracy without a system prompt, and 84.8% with a system prompt. The small 0.6% gap highlights the model’s stability and reliability across prompting conditions — a critical property for real-world deployments where system prompts may vary.
Chat & Instruction Following
Quick Start
Recommended Inference Parameters
temperature: 0.6
top_p: 0.95
top_k: 20
min_p: 0.0
max_tokens: 2048
🤝 Community & Support
- Discussions: HuggingFace Community
- Jan App: Discover more about the Jan App at jan.ai
📄 Citation
Updated Soon