alternatives: Use local inference via llama.cpp, or convert model to safetensors format
  for HF Inference API support.
base_model: qwen2.5-coder-1.5b-instruct
eval_type: inference-check
http_status: 400
inference_api_dns_resolved: true
inference_api_supported: false
inference_router_endpoint: https://router.huggingface.co/hf-inference/models/Nanthasit/sakthai-coder-1.5b
model: Nanthasit/sakthai-coder-1.5b
model_format: GGUF
prompt: Write a Python function to check if a number is prime.
quantization: Q4_K_M
reason: 'Model is GGUF format (qwen2.5-coder-1.5b-instruct-q4_k_m.gguf) and is not
  supported by HF serverless Inference API. The hf-inference provider returned: Model
  not supported by provider hf-inference.'
response_time_ms: 282
status: unavailable
timestamp: 20260730T235122Z