qwen3.5-0.8b-intent-classification

# Download the model
huggingface-cli download Nikhil1581/qwen3.5-0.8b-intent-classification Qwen3.5-0.8B.Q4_K_M.gguf --local-dir ./models

# Run inference
./llama-cli -m ./models/Qwen3.5-0.8B.Q4_K_M.gguf \
  -p "Classify the intent of the following message: 'What is the weather like today?'" \
  -n 128

from llama_cpp import Llama

llm = Llama(
    model_path="./models/Qwen3.5-0.8B.Q4_K_M.gguf",
    n_ctx=2048,
)

prompt = """You are an intent classification assistant. 
Classify the intent of the user message below into a single intent label.

User message: "Book me a flight to New York for next Monday."
Intent:"""

output = llm(prompt, max_tokens=64, stop=["\n"])
print(output["choices"][0]["text"].strip())

# Create a Modelfile
cat <<EOF > Modelfile
FROM ./models/Qwen3.5-0.8B.Q4_K_M.gguf
SYSTEM "You are an intent classification assistant. Given a user message, respond with the most appropriate intent label."
EOF

ollama create qwen-intent -f Modelfile
ollama run qwen-intent "Cancel my subscription"

@misc{nikhil1581-qwen3.5-intent,
  author       = {Nikhil1581},
  title        = {Qwen3.5-0.8B Intent Classification (GGUF)},
  year         = {2026},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/Nikhil1581/qwen3.5-0.8b-intent-classification}
}