🐙 Google Turboquants

services:
  llama-cpp:
    image: llama-cpp:turboquants
    container_name: llama-cpp
    ports:
      - 8080:8080
    privileged: true
    ipc: host
    volumes:
      - /mnt/data/files/models:/app/models
    command: -m
      /app/models/unsloth/Qwen3.6-35B-A3B-MTP-GGUF/Qwen3.6-35B-A3B-UD-IQ4_NL.gguf
      --port 8080 --host 0.0.0.0  -t 12 -c 262144 --parallel
      1  --no-context-shift --no-mmap --jinja  -b 4096 -ub 2048  -ngl 999
      --cpu-moe -ctk turbo3 -ctv turbo2 --spec-type draft-mtp --spec-draft-n-max
      3 --kv-unified --cache-ram 0
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    restart: unless-stopped