GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
flywheel-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
flywheel-ai
Model Tree
Qwen/Qwen3.6-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
bash
pip install -U huggingface_hubhf download flywheel-ai/healthcare-frontdesk # full repo (safetensors + GGUF)hf download flywheel-ai/healthcare-frontdesk model-q4_k_m.gguf # just the GGUF
bash
# llama.cppllama-server -m model-q4_k_m.gguf -ngl 999# Ollama (pulls the GGUF straight from HF)ollama run hf.co/flywheel-ai/healthcare-frontdesk# vLLM (serves the safetensors)vllm serve flywheel-ai/healthcare-frontdesk
Front desk, never a clinician; refuses all clinical, triage, and medication questions and routes them to the provider, a nurse line, or 911 for emergencies.
v1.0 is trained on synthetic seed data authored by permissively-licensed local models (Apache/MIT teachers only — never distilled from closed models). On general prompts it is roughly on par with the base; the niche edge sharpens as consented real usage flows through the OpSpot flywheel. Built on Qwen3.6 (Apache-2.0).