flywheel-ai/beauty-wellness

TEXT GENERATIONConcurrent Unit Cost:3Model Size:35.1BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 20, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The flywheel-ai/beauty-wellness model is a 35.1 billion parameter language model developed by Flywheel by OpSpot. It is fine-tuned from Qwen/Qwen3.6-35B-A3B specifically for the beauty-wellness domain. This model is designed as a vertical AI-employee, excelling in specialized tasks and knowledge within its niche. It is built on synthetic seed data from permissively-licensed local models, with performance sharpening through real usage.

Loading preview...

Overview

The flywheel-ai/beauty-wellness model is a 35.1 billion parameter language model developed by Flywheel by OpSpot. It is a specialized "vertical AI-employee" model, fine-tuned from the Qwen/Qwen3.6-35B-A3B base model (Apache-2.0 license) specifically for the beauty-wellness domain.

Key Characteristics

  • Domain-Specific: Optimized for tasks and knowledge within the beauty-wellness industry.
  • Provenance: Initial training utilized synthetic seed data generated by permissively-licensed local models (Apache/MIT teachers), avoiding distillation from closed-source models.
  • Performance Evolution: While roughly on par with its base model on general prompts, its niche performance is designed to improve with consented real-world usage through the OpSpot flywheel.
  • Formats: Available in safetensors format for transformers and vLLM, and model-q4_k_m.gguf for llama.cpp and Ollama.

Use Cases

This model is particularly well-suited for applications requiring deep, specialized knowledge in the beauty and wellness sectors. Developers can leverage it for:

  • Building AI assistants or chatbots focused on beauty and wellness inquiries.
  • Content generation for beauty-wellness related topics.
  • Specialized data analysis or information retrieval within the domain.

Finetunes
1 models