healthCheckTimeout: 180
logLevel: info

models:
  "qwen3.5:9b":
    cmd: |
      /app/llama-server
      --host 0.0.0.0 --port ${PORT}
      --model /models/Qwen3.5-9B-Q4_K_M.gguf
      --mmproj /models/Qwen3.5-9B-mmproj-F16.gguf
      --alias qwen3.5:9b
      --n-gpu-layers 999
      --ctx-size 8192
      --flash-attn on
      --jinja
      --temp 0.7 --top-p 0.9

  "qwen3.5:9b-32k":
    cmd: |
      /app/llama-server
      --host 0.0.0.0 --port ${PORT}
      --model /models/Qwen3.5-9B-Q4_K_M.gguf
      --mmproj /models/Qwen3.5-9B-mmproj-F16.gguf
      --alias qwen3.5:9b-32k
      --n-gpu-layers 999
      --ctx-size 32768
      --flash-attn on
      --jinja
      --cache-type-k q8_0
      --cache-type-v q8_0
      --temp 0.7 --top-p 0.9

  "qwen3.5:9b-uncensored":
    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
      --flash-attn on
      --jinja
      --cache-type-k q8_0
      --cache-type-v q8_0
      --temp 0.7 --top-p 0.9

  "qwen3.5:9b-claude-4.6-opus-reasoning":
    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
      --flash-attn on
      --jinja
      --cache-type-k q8_0
      --cache-type-v q8_0
      --temp 0.6 --top-p 0.95

  "qwen3.5:9b-128k":
    cmd: |
      /app/llama-server
      --host 0.0.0.0 --port ${PORT}
      --model /models/Qwen3.5-9B-Q4_K_M.gguf
      --mmproj /models/Qwen3.5-9B-mmproj-F16.gguf
      --alias qwen3.5:9b-128k
      --n-gpu-layers 999
      --ctx-size 131072
      --flash-attn on
      --jinja
      --cache-type-k q8_0
      --cache-type-v q8_0
      --temp 0.7 --top-p 0.9

  "qwen3.5:9b-uncensored-128k":
    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 131072
      --flash-attn on
      --jinja
      --cache-type-k q8_0
      --cache-type-v q8_0
      --temp 0.7 --top-p 0.9

  "qwen3.5:9b-claude-4.6-opus-reasoning-128k":
    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 131072
      --flash-attn on
      --jinja
      --cache-type-k q8_0
      --cache-type-v q8_0
      --temp 0.6 --top-p 0.95

  "gemma4:e4b-uncensored":
    cmd: |
      /app/llama-server
      --host 0.0.0.0 --port ${PORT}
      --model /models/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf
      --mmproj /models/mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf
      --alias "hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:q8_k_p"
      --n-gpu-layers 999
      --ctx-size 8192
      --flash-attn on
      --jinja

  "gemma4:26b-a4b":
    cmd: |
      /app/llama-server
      --host 0.0.0.0 --port ${PORT}
      --model /models/gemma-4-26B-A4B-it-UD-IQ4_NL.gguf
      --mmproj /models/gemma-4-26B-A4B-it-UD-IQ4_NL-mmproj-BF16.gguf
      --alias "hf.co/unsloth/gemma-4-26B-A4B-it:ud-iq4_nl"
      --n-gpu-layers 999
      --ctx-size 8192
      --flash-attn on
      --jinja