{
  "default_model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
  "models": {
    "meta-llama/Meta-Llama-3.1-8B-Instruct": {
      "ctx": "65536",
      "trust_remote": false,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "32768"
    },
    "openai/gpt-oss-20b": {
      "ctx": "32768",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "8192"
    },
    "RedHatAI/Qwen3-14B-FP8-dynamic": {
      "ctx": "32768",
      "trust_remote": true,
      "valid_tp": [1],
      "max_num_seqs": "64",
      "max_tokens": "32768"
    },
    "cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit": {
      "ctx": "24576",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "32768"
    },
    "cpatonn/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit": {
      "ctx": "20480",
      "trust_remote": true,
      "valid_tp": [2],
      "max_num_seqs": "32",
      "max_tokens": "16384",
      "enforce_eager": false,
      "env": {"VLLM_USE_TRITON_AWQ": "1"}
    },
    "RedHatAI/gemma-3-27b-it-FP8-dynamic": {
      "ctx": "29000",
      "trust_remote": true,
      "valid_tp": [2],
      "max_num_seqs": "32",
      "max_tokens": "29000",
      "gpu_util": "0.94"
    },
    "RedHatAI/gemma-3-12b-it-FP8-dynamic": {
      "ctx": "9900",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "9900"
    }
  }
}