# Demo: Qwen3.8-Flash-Next GSQ-RCO Coder (Pruned GGUF) – über die lokale Ollama-API (Ollama muss laufen)
import requests

r = requests.post("http://localhost:11434/api/chat", json={
    "model": "hf.co/Skyrion/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF-Pruned",
    "messages": [{"role": "user", "content": "Erkläre in drei Sätzen, was ein Large Language Model ist."}],
    "stream": False,
}, timeout=600)
r.raise_for_status()
print(r.json()["message"]["content"])