healthCheckTimeout: 180
logLevel: info

models:
  # NOTE: qwen3.5:9b and qwen3.5:9bctxSmall are disabled — the GGUF extracted
  # from Ollama uses the old mrope_sections format (3 elements) which this
  # llama.cpp build rejects. Download a fresh quantization from HuggingFace
  # (e.g. bartowski/Qwen3.5-9B-GGUF) and add them back.

  "hf.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:q4_k_m":
    cmd: |
      /app/llama-server
      --host 0.0.0.0 --port ${PORT}
      --model /models/HauhauCS-Qwen3.5-9B-Uncensored-Aggressive.q4_k_m.gguf
      --mmproj /models/HauhauCS-Qwen3.5-9B-Uncensored-Aggressive.mmproj.gguf
      --alias "hf.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:q4_k_m"
      --n-gpu-layers 999
      --ctx-size 32768

  "hf.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF:q4_k_m":
    cmd: |
      /app/llama-server
      --host 0.0.0.0 --port ${PORT}
      --model /models/Jackrong-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.q4_k_m.gguf
      --mmproj /models/Jackrong-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.mmproj.gguf
      --alias "hf.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF:q4_k_m"
      --n-gpu-layers 999
      --ctx-size 32768
      --temp 0.6 --top-k 20 --top-p 0.95 --repeat-penalty 1