{
  "id": "qwen38-24t-vllm",
  "title": "Qwen3.8-2.4T-A95B: vLLM recipe",
  "kind": "deployment",
  "source_type": "maintainer_recipe",
  "summary": "Large MoE recipe with explicit multi-GPU strategies and distinct native versus extended context claims.",
  "runtime": "vLLM",
  "runtime_topics": [
    "vLLM"
  ],
  "hardware_topics": [
    "amd",
    "nvidia"
  ],
  "platform_topics": [
    "linux"
  ],
  "model_label": "Qwen3.8-2.4T-A95B",
  "model_family": "Qwen",
  "model_id": "Qwen/Qwen3.8-2.4T-A95B",
  "model_release_date": null,
  "model_artifact": {
    "id": "Qwen/Qwen3.8-2.4T-A95B",
    "revision": null,
    "format": "bf16"
  },
  "evidence_state": "source_reported",
  "site_reproduced": false,
  "record_type": "curated_reference",
  "performance_ranking_allowed": false,
  "metrics": null,
  "metrics_status": "site_metrics_unmeasured; attributed_source_figures_in_editorial.reported_results",
  "conditions": {
    "model_revision": null,
    "weight_hash": null,
    "runtime_execution_revision": null,
    "input_tokens": null,
    "output_tokens": null,
    "concurrency": null,
    "cache_state": null,
    "quantization": null,
    "speculative_decoding": null,
    "temperature": null,
    "top_p": null
  },
  "reported_setup": {
    "system": null,
    "node_count": null,
    "parallelism": null,
    "kv_dtype": null,
    "context_limit_tokens": null,
    "experiment_date": null
  },
  "test_profiles": [],
  "deployment_options": [
    {
      "variant": "default",
      "model_id": "Qwen/Qwen3.8-2.4T-A95B",
      "precision": "bf16",
      "supported_hardware": null,
      "model_revision": null,
      "declared_planning_minimum_gb": 5871,
      "minimum_runtime_version": "nightly",
      "extra_args": [],
      "tensor_parallel_by_hardware": null
    },
    {
      "variant": "fp8",
      "model_id": "Qwen/Qwen3.8-2.4T-A95B-FP8",
      "precision": "fp8",
      "supported_hardware": null,
      "model_revision": null,
      "declared_planning_minimum_gb": 2996,
      "minimum_runtime_version": "nightly",
      "extra_args": [],
      "tensor_parallel_by_hardware": null
    },
    {
      "variant": "mxfp4",
      "model_id": "Inferact/Qwen3.8-2.4T-A95B-MXFP4",
      "precision": "mxfp4",
      "supported_hardware": [
        "mi300x",
        "mi325x",
        "mi355x"
      ],
      "model_revision": null,
      "declared_planning_minimum_gb": 1917,
      "minimum_runtime_version": "nightly",
      "extra_args": [],
      "tensor_parallel_by_hardware": null
    },
    {
      "variant": "nvfp4",
      "model_id": "Inferact/Qwen3.8-2.4T-A95B-NVFP4",
      "precision": "nvfp4",
      "supported_hardware": [
        "b200",
        "b300",
        "gb200",
        "gb300"
      ],
      "model_revision": null,
      "declared_planning_minimum_gb": 1737,
      "minimum_runtime_version": "nightly",
      "extra_args": [
        "--linear-backend",
        "flashinfer_cutedsl"
      ],
      "tensor_parallel_by_hardware": null
    },
    {
      "variant": "nvfp4_reap25",
      "model_id": "RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-25",
      "precision": "nvfp4",
      "supported_hardware": [
        "b200",
        "b300",
        "gb200",
        "gb300"
      ],
      "model_revision": null,
      "declared_planning_minimum_gb": 1373,
      "minimum_runtime_version": "nightly",
      "extra_args": [],
      "tensor_parallel_by_hardware": null
    }
  ],
  "recipe_parameters": {
    "minimum_runtime_version": "nightly",
    "nightly_required": true,
    "model_context_limit_tokens": 262144,
    "compatible_strategies": [
      "single_node_tp",
      "single_node_tep",
      "single_node_dep",
      "multi_node_tp",
      "multi_node_tep",
      "multi_node_dep",
      "multi_node_tp_pp",
      "multi_node_tp_dp",
      "pd_cluster"
    ],
    "hardware_claims": [
      {
        "profile": "b300",
        "maintainer_status": "verified"
      },
      {
        "profile": "gb300",
        "maintainer_status": "verified"
      }
    ],
    "recipe_updated_on": "2026-09-14",
    "effective_default_minimum_runtime_version": "nightly"
  },
  "measurement_scope": "deployment_reference",
  "notes": [
    "Recipe minimum engine version: nightly.",
    "Default artifact: Qwen/Qwen3.8-2.4T-A95B.",
    "Variant and hardware settings are source declarations; select the matching original profile."
  ],
  "limitations": [
    "Nightly is required by this pinned recipe.",
    "A four-GPU NVL4 tray is not an eight-GPU server; retain the actual topology.",
    "Input length, output policy, concurrency and cache are workload-specific; no single benchmark is inferred from the recipe."
  ],
  "comparison_status": "not_comparable",
  "editorial_status": "source_derived_detailed_article",
  "public_benchmark_snapshot": false,
  "source": {
    "publisher": "vllm-project",
    "url": "https://github.com/vllm-project/recipes",
    "repository": "vllm-project/recipes",
    "platform": "github",
    "revision": "d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94",
    "document_path": "models/Qwen/Qwen3.8-2.4T-A95B.yaml",
    "pinned_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml",
    "report_url": null,
    "document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2",
    "last_commit_at": "2026-10-17T09:22:45Z",
    "checked_on": "2026-10-17",
    "metadata_status": "checked"
  },
  "license": {
    "declared_spdx": "Apache-2.0",
    "scope": "Recipe repository only; each model and conversion has independent distribution terms."
  },
  "editorial": {
    "version": 1,
    "published_on": "2026-10-17",
    "modified_on": "2026-10-17",
    "byline": "Run AI Here editorial",
    "creation_method": "AI-assisted source reading and original editorial synthesis; no independent model execution.",
    "answer": "The pinned Qwen3.8-2.4T-A95B recipe defaults to Qwen/Qwen3.8-2.4T-A95B (bf16). Its effective default-variant minimum is vLLM nightly. Select the exact variant, hardware override and topology before treating it as a launch plan. No deployment was run by this site.",
    "sections": [
      {
        "heading": "Which artifact and engine does this recipe select?",
        "paragraphs": [
          "The recipe identifies Qwen/Qwen3.8-2.4T-A95B as its model family entry and selects Qwen/Qwen3.8-2.4T-A95B by default. The default precision label is bf16; model-wide and variant-specific runtime requirements are kept separately below. The document revision fixes what the recipe said, while the weight revision and executed runtime revision remain separate fields. A model-family title alone cannot establish either artifact identity."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L102"
        ]
      },
      {
        "heading": "What needs special attention for this model?",
        "paragraphs": [
          "This recipe requires nightly vLLM and a very large distributed deployment. Its native window is 262,144 tokens; the separate 1M extension has its own validation boundary. The default describes 24 GPUs as three eight-GPU B300 nodes or six four-GPU GB300 NVL4 trays. A tray is not an eight-GPU node, and total cluster capacity is not one automatically pooled memory space."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L31"
        ]
      },
      {
        "heading": "How should the settings be applied?",
        "paragraphs": [
          "Choose one artifact variant and one hardware profile from the original recipe, then resolve its shared, variant, hardware, strategy and optional-feature settings together. The base arguments listed here are only one layer and are deliberately not presented as a complete runnable command. Check any nightly-image requirement and the model’s parsers before loading weights. A context declaration is a model limit, while batched-token and sequence settings control a serving workload."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L159"
        ]
      },
      {
        "heading": "What does the memory number mean?",
        "paragraphs": [
          "The GB figure is the recipe’s declared planning minimum for the selected variant. It is not a site measurement, a universal peak allocation or a promise of maximum context. KV cache, auxiliary/draft models, image encoders, temporary workspace and active requests still require memory. Keep GB and GiB distinct, and use the actual artifact size and runtime allocation for a machine-specific budget."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L106"
        ]
      },
      {
        "heading": "What is needed to reproduce a deployment?",
        "paragraphs": [
          "Save the model and conversion revisions, weight hashes, tokenizer/template, container or runtime digest, device count/topology and complete resolved launch. First check one short public request. For a subsequent measurement, fix input and output counts, concurrency, cache state, warmup, sampling, reasoning effort, repetitions and failures. The declarations on this page are source configuration facts; no throughput or quality outcome follows from them."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L237"
        ]
      }
    ],
    "facts": [
      {
        "name": "Architecture",
        "value": "moe",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L50",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Total parameters as counted by recipe",
        "value": "2.4T",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L51",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Active parameters as counted by recipe",
        "value": "95B",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L52",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Native context declaration (tokens)",
        "value": 262144,
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L57",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Model-wide minimum vLLM",
        "value": "nightly",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L44",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Effective default-variant minimum vLLM",
        "value": "nightly",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L44",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Default artifact",
        "value": "Qwen/Qwen3.8-2.4T-A95B",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L102",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Default precision label",
        "value": "bf16",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L102",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Default planning minimum (GB; recipe declaration)",
        "value": 5871,
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L106",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Default variant hardware allowlist",
        "value": null,
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L102",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Shared base arguments (incomplete launch)",
        "value": [],
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L102",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Declared compatible strategies",
        "value": [
          "single_node_tp",
          "single_node_tep",
          "single_node_dep",
          "multi_node_tp",
          "multi_node_tep",
          "multi_node_dep",
          "multi_node_tp_pp",
          "multi_node_tp_dp",
          "pd_cluster"
        ],
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L102",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Optional feature names",
        "value": [
          "tool_calling",
          "reasoning",
          "spec_decoding"
        ],
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L102",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      },
      {
        "name": "Features selected by default",
        "value": [
          "spec_decoding"
        ],
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/Qwen/Qwen3.8-2.4T-A95B.yaml#L102",
        "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
      }
    ],
    "reported_results": [],
    "source_document_sha256": "dbaaa7ecb550abcd5a38bc81480b6c94799064883d215d42e67f929bfe393fb2"
  }
}