flywheel-ai/healthcare-frontdesk
The flywheel-ai/healthcare-frontdesk model is a 35.1 billion parameter language model developed by Flywheel by OpSpot, fine-tuned from Qwen/Qwen3.6-35B-A3B. This model is specifically optimized as a vertical AI-employee for the healthcare front-desk domain. It excels at tasks such as appointment scheduling, patient onboarding, insurance inquiries, and billing questions, while adhering to strict guardrails against clinical advice.
Loading preview...
Overview
The flywheel-ai/healthcare-frontdesk model is a specialized 35.1 billion parameter AI developed by Flywheel by OpSpot. It is fine-tuned (LoRA) from the Qwen/Qwen3.6-35B-A3B base model, focusing on the unique requirements of a healthcare front-desk assistant. This model is designed to act as a warm, AI-powered employee for medical and dental offices.
Key Capabilities
- Appointment Management: Handles scheduling and rescheduling of patient appointments.
- Patient Onboarding: Assists with intake processes and new-patient registration.
- Insurance & Billing: Addresses inquiries regarding insurance eligibility and billing questions.
- General Information: Provides information on office hours, directions, and routes prescription refill requests.
- Guardrails: Strictly refuses clinical, triage, and medication questions, routing them to appropriate medical personnel or emergency services.
Provenance & Honesty
This model's v1.0 was trained using synthetic seed data generated by permissively-licensed local models (Apache/MIT teachers only), ensuring no distillation from closed models. While its general performance is comparable to its base model, its specialized capabilities are enhanced by real usage data flowing through the OpSpot flywheel. The model is available in safetensors format for transformers and vLLM, and model-q4_k_m.gguf for llama.cpp and Ollama.