{
  "schema": "onefrontier.launch-card/v1",
  "hf": {
    "repo": "Qwen/Qwen3.8-27B",
    "revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
    "license": "apache-2.0",
    "gated": false,
    "params_b": 27.78,
    "modality": [
      "image-text-to-text"
    ],
    "weight_gib": 51.7,
    "last_modified": "2026-08-14T15:00:01.000Z",
    "downloads": 7581050
  },
  "checkpoints": [
    {
      "name": "root",
      "format": "bf16",
      "subdir": null,
      "source_repo": null,
      "resident_gib": 51.7,
      "host_gib": null,
      "gated": false,
      "notes": "18 weight file(s)"
    }
  ],
  "envs": [
    {
      "engine": "vllm",
      "checkpoint": "root",
      "engine_version": null,
      "image": "vllm/vllm-openai:qwen38",
      "argv": [
        "vllm",
        "serve",
        "Qwen/Qwen3.8-27B",
        "--tensor-parallel-size",
        "1",
        "--enable-auto-tool-choice",
        "--tool-call-parser",
        "qwen3_coder",
        "--reasoning-parser",
        "qwen3",
        "--mm-encoder-tp-mode",
        "data"
      ],
      "command": "vllm serve Qwen/Qwen3.8-27B \\\n  --tensor-parallel-size 1 \\\n  --enable-auto-tool-choice \\\n  --tool-call-parser qwen3_coder \\\n  --reasoning-parser qwen3 \\\n  --mm-encoder-tp-mode data",
      "env": {
        "VLLM_USE_RUST_FRONTEND": "1"
      },
      "validated_hardware": [
        "gb300",
        "b200",
        "rtx_5090",
        "rtx_5090_2x",
        "rtx_pro_6000",
        "dgx_spark_gb10",
        "ascend_950pr",
        "arc_pro_b60",
        "arc_pro_b70"
      ],
      "notes": null,
      "source": {
        "kind": "vllm-recipes",
        "url": "https://recipes.vllm.ai/Qwen/Qwen3.8-27B.json",
        "fetched_at": null
      }
    }
  ],
  "hardware": {
    "gpu_models": [
      "b200",
      "gb300",
      "rtx_5090",
      "rtx_5090_2x",
      "rtx_pro_6000"
    ],
    "gpu_arch": [
      "blackwell"
    ],
    "min_gpus": 1,
    "tp_rule": "widest published TP is 1",
    "min_vram_per_gpu_gib": null,
    "min_total_vram_gib": null,
    "min_disk_gib": 112,
    "min_host_ram_gib": null,
    "interconnect": null,
    "cuda_min": null,
    "driver_min": null,
    "context_tokens": null
  },
  "performance": "https://onefrontier.ai/Qwen/Qwen3.8-27B/performance",
  "evidence": [
    {
      "kind": "hf-api",
      "url": "https://huggingface.co/api/models/Qwen/Qwen3.8-27B",
      "fetched_at": null
    },
    {
      "kind": "vllm-recipes",
      "url": "https://recipes.vllm.ai/Qwen/Qwen3.8-27B.json",
      "fetched_at": null
    },
    {
      "kind": "sglang-cookbook",
      "url": "https://docs.sglang.io/cookbook/autoregressive/Qwen/Qwen3.8-27B.md",
      "fetched_at": null
    }
  ],
  "gaps": [
    {
      "field": "envs.sglang",
      "why": "SGLang cookbook page exists but its launch command is generated by the page's Deploy widget, not printed in the markdown; the page documents these flags: --mamba-full-memory-ratio, --speculative-num-draft-tokens, --speculative-dspark-block-size, --enable-linear-replayssm-spec, --mamba-ssm-dtype, --max-mamba-cache-size, --max-running-requests, --mem-fraction-static, --max-total-tokens, --kv-cache-dtype, --attention-backend, --device, --speculative-algorithm, --tp-size..."
    },
    {
      "field": "hardware.npu",
      "why": "recipes name non-GPU accelerators too: arc_pro_b60, arc_pro_b70, ascend_950pr, dgx_spark_gb10 (not carded)"
    }
  ],
  "captured_at": "2026-10-31T17:28:18Z",
  "captured_by": "hf-api + vllm-recipes + sglang-cookbook"
}