amd-r9700-vllm-toolboxes/config.json

{
  "default_model": "Qwen3.5-35B-A3B-GPTQ-Int4",
  "models": {
    "gpt-oss-20b": {
      "ctx": "32768",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "8192",
      "hf_model_id": "openai/gpt-oss-20b"
    },
    "Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit": {
      "ctx": "24576",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "32768",
      "hf_model_id": "cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit"
    },
    "DeepSeek-R1-Distill-Qwen-14B": {
      "ctx": "32768",
      "trust_remote": true,
      "valid_tp": [1],
      "max_num_seqs": "64",
      "max_tokens": "32768",
      "hf_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
    },
    "DeepSeek-R1-Distill-Qwen-32B-AWQ": {
      "ctx": "24576",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "32768",
      "hf_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B-AWQ"
    },
    "GLM-4.7-Flash-AWQ": {
      "ctx": "32768",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "32768",
      "hf_model_id": "THUDM/GLM-4.7-Flash-AWQ"
    },
    "Qwen3.5-35B-A3B-GPTQ-Int4": {
      "ctx": "32768",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "32768",
      "hf_model_id": "Qwen/Qwen3.5-35B-A3B-GPTQ-Int4"
    },
    "Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit": {
      "ctx": "24576",
      "trust_remote": true,
      "valid_tp": [1, 2],
      "max_num_seqs": "64",
      "max_tokens": "32768",
      "hf_model_id": "Qwen/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit"
    }
  }
}