A vLLM Docker Compose recipe for running Qwen 3.6 27B on dual RTX 3090s (+OpenCode configuration)

services:
  vllm-qwen36:
    image: vllm/vllm-openai:latest
    container_name: vllm-qwen36
    ipc: host
    shm_size: 32gb
    ports:
      - "8337:8000"
    volumes:
      - /opt/docker/data/vllm/cache/huggingface:/root/.cache/huggingface
      - /opt/docker/data/vllm/cache/vllm:/root/.cache/vllm
    environment:
      VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['0', '1']
              capabilities: [gpu]
    command: cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4 --tensor-parallel-size 2 --max-model-len 262144 --gpu-memory-utilization 0.98 --mm-encoder-tp-mode data  --kv-cache-dtype fp8 --enable-prefix-caching --enable-chunked-prefill --max-num-batched-tokens 4096 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --max-num-seqs 2 --speculative-config '{"method":"mtp","num_speculative_tokens":1}'

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "dzai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "DzAI",
      "options": {
        "baseURL": "http://dzai.my-tailnet.ts.net:8337/v1"
      },
      "models": {
        "cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4": {
          "name": "Qwen3.6 27B (256k)",
          "tools": true,
          "reasoning": true,
          "limit": { "context": 262144, "output": 32768 },
          "options": {
            "temperature": 0.6,
            "top_p": 0.95,
            "extraBody": {
              "top_k": 20,
              "presence_penalty": 0.0,
              "chat_template_kwargs": { "enable_thinking": true }
            }
          }
        }
      }
    }
  }
}