models:
  gpu-vision:
    gpu_url: http://192.168.68.110:8080/v1
    gpu_host: 192.168.68.110
    label: Qwen3.5-9B Vision (RTX 5070)
    max_concurrent: 1
    context: 131072
    tiers: [starter, professional, enterprise]
    capabilities: [completion, multimodal]
    model_path: /home/llmuser/models/qwen3.5-9b/Qwen3.5-9B-Q5_K_M.gguf
    args: --mmproj /home/llmuser/models/qwen3.5-9b/mmproj-F16.gguf --ctx-size 131072 --cache-type-k q4_0 --cache-type-v q4_0 --batch-size 2048 --ubatch-size 1024 --n-gpu-layers 99 --flash-attn 1 --cont-batching --parallel 1 --image-min-tokens 2048 --image-max-tokens 16384 --alias gpu-light --reasoning off --api-key not-needed --predict 8192 --cache-prompt --port 8080 --host 0.0.0.0

  gpu-dense:
    gpu_url: http://192.168.68.8:8080/v1
    sidecar_url: http://192.168.68.8:8090
    gpu_host: 192.168.68.8
    label: Qwen3.8-27B-Uncensored (RTX 3090)
    max_concurrent: 1
    context: 131072
    tiers: [professional, enterprise]
    capabilities: [completion]
    model_path: /home/llmuser/models/Qwen3.8-27B-Uncensored-Q4_K_M.gguf
    args: -m /home/llmuser/models/Qwen3.8-27B-Uncensored-Q4_K_M.gguf -c 131072 --host 0.0.0.0 --port 8080 -ngl 99 --alias qwen3.6-27B-code --api-key not-needed -ctk q4_0 -ctv q4_0 --flash-attn on --cont-batching --parallel 1 --slot-save-path /home/llmuser/.llama-slots --metrics --reasoning off --spec-type draft-mtp --spec-draft-n-max 2 -t 8

  strix-moe:
    gpu_url: http://192.168.68.15:8080/v1
    sidecar_url: http://192.168.68.15:8090
    gpu_host: 192.168.68.15
    label: Carnice Qwen3.6 MoE 35B-A3B (Strix Halo)
    max_concurrent: 1
    context: 262144
    tiers: [professional, enterprise]
    capabilities: [completion, multimodal]
    model_path: /models/Carnice-Qwen3.6-MoE-35B-A3B-Q4_K_M.gguf
    args: -m /models/Carnice-Qwen3.6-MoE-35B-A3B-Q4_K_M.gguf --host 0.0.0.0 --port 8080 --alias strix-moe -c 262144 -ngl 99 -fa on --cache-type-k q4_0 --cache-type-v q4_0 --kv-unified --cache-prompt --cont-batching -b 4096 --ubatch-size 1024 --parallel 2 -t 16 --timeout 600 -n 8192 --reasoning off --no-warmup --metrics

hosts:
  gpu-light:
    address: 192.168.68.110
    gpu_name: NVIDIA GeForce RTX 5070
    vram_gb: 12
    current_model: gpu-vision

  gpu-dense:
    address: 192.168.68.8
    gpu_name: NVIDIA GeForce RTX 3090
    vram_gb: 24
    current_model: gpu-dense

  gpu-moe:
    address: 192.168.68.15
    gpu_name: AMD Strix Halo (iGPU)
    vram_gb: 64
    current_model: strix-moe