flywheel-ai/agency-ops

TEXT GENERATIONConcurrency Cost:3Model Size:35.1BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 20, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The flywheel-ai/agency-ops model is a 35.1 billion parameter language model fine-tuned from Qwen/Qwen3.6-35B-A3B by Flywheel by OpSpot. This model is specifically optimized as a vertical AI-employee for agency operations, focusing on tasks like lead generation, client onboarding, proposal generation, and workflow management. It excels as an operator and advisor for AI-automation agencies, providing specialized support for business processes. The model has a context length of 32768 tokens and is available in safetensors and GGUF formats.

Loading preview...

Overview

The flywheel-ai/agency-ops model is a 35.1 billion parameter, open-source vertical AI-employee model developed by Flywheel by OpSpot. It is fine-tuned (LoRA) from the Qwen/Qwen3.6-35B-A3B base model, specifically tailored for the agency-ops domain. This model functions as a sharp operator and advisor for AI-automation agencies.

Key Capabilities

  • Specialized Agency Operations: Optimized for tasks such as lead generation and qualification, discovery and scoping, pricing and packaging, proposals and SOWs, client onboarding, and building/shipping agent workflows.
  • Business Process Support: Handles tooling and integrations, delivery/QA, support and retention, and general agency management.
  • Synthetic Data Training: The v1.0 model is trained on synthetic seed data authored by permissively-licensed local models (Apache/MIT teachers only), ensuring no distillation from closed models.
  • Guardrails: Includes a guardrail to defer to qualified professionals for legal, financial, and tax advice.

Good For

  • AI-automation agencies seeking an intelligent assistant for operational tasks.
  • Automating and streamlining various stages of client engagement and project delivery.
  • Generating specialized content related to agency business processes.

Technical Details

  • Base Model: Qwen/Qwen3.6-35B-A3B
  • License: Apache-2.0
  • Formats: Available in safetensors (for transformers/vLLM) and model-q4_k_m.gguf (for llama.cpp/Ollama).