kleverboots/nope-edge-phi4-v1-gguf

NOPE Edge Phi4 v1 - GGUF

Quantized version of kleverboots/nope-edge-phi4-v1 for llama.cpp inference.

Files

File	Quantization	Size
model-Q4_K_M.gguf	Q4_K_M	2.32 GB

Usage with llama.cpp

# Download
huggingface-cli download kleverboots/nope-edge-phi4-v1-gguf model-Q4_K_M.gguf --local-dir .

# Run server
llama-server -m model-Q4_K_M.gguf -ngl 99 -c 4096

# Query
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "test"}]}'

Source Model

• Repository: kleverboots/nope-edge-phi4-v1
• Base: microsoft/Phi-4-mini-instruct
• Purpose: Mental health crisis classification

License

MIT (same as source model)