{
  "schema": "onefrontier.launch-card/v1",
  "hf": {
    "repo": "zai-org/GLM-5.3-Flash",
    "revision": "46a050bec13002ad29ee795c16e61cf4fa3c4a9c",
    "license": "mit",
    "gated": false,
    "params_b": 321.32,
    "modality": [
      "image-text-to-text"
    ],
    "weight_gib": 305.8,
    "last_modified": "2026-10-15T06:32:52.000Z",
    "downloads": 6360678
  },
  "checkpoints": [
    {
      "name": "root",
      "format": "bf16",
      "subdir": null,
      "source_repo": null,
      "resident_gib": 305.8,
      "host_gib": null,
      "gated": false,
      "notes": "62 weight file(s)"
    }
  ],
  "envs": [
    {
      "engine": "vllm",
      "checkpoint": "root",
      "engine_version": null,
      "image": "vllm/vllm-openai:nightly",
      "argv": [
        "vllm",
        "serve",
        "zai-org/GLM-5.3-Flash",
        "--tokenizer-mode",
        "glm5_next",
        "--tensor-parallel-size",
        "8",
        "--disable-flashinfer-autotune",
        "--tool-call-parser",
        "glm47",
        "--enable-auto-tool-choice",
        "--reasoning-parser",
        "glm47"
      ],
      "command": "vllm serve zai-org/GLM-5.3-Flash \\\n  --tokenizer-mode glm5_next \\\n  --tensor-parallel-size 8 \\\n  --disable-flashinfer-autotune \\\n  --tool-call-parser glm47 \\\n  --enable-auto-tool-choice \\\n  --reasoning-parser glm47",
      "env": {
        "VLLM_ENGINE_READY_TIMEOUT_S": "3600",
        "VLLM_USE_RUST_FRONTEND": "1"
      },
      "validated_hardware": [
        "h100",
        "b200",
        "gb200",
        "mi355x",
        "ascend_950pr_8x"
      ],
      "notes": null,
      "source": {
        "kind": "vllm-recipes",
        "url": "https://recipes.vllm.ai/zai-org/GLM-5.3-Flash.json",
        "fetched_at": null
      }
    },
    {
      "engine": "sglang",
      "checkpoint": "root",
      "engine_version": null,
      "image": "lmsysorg/sglang:latest",
      "argv": [
        "sglang",
        "serve",
        "--model-path",
        "zai-org/GLM-5.3-Flash",
        "--tp-size",
        "4",
        "--encoder-only",
        "--host",
        "0.0.0.0",
        "--port",
        "30001"
      ],
      "command": "sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --encoder-only --host 0.0.0.0 --port 30001",
      "env": {},
      "validated_hardware": [],
      "notes": null,
      "source": {
        "kind": "sglang-cookbook",
        "url": "https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.3-Flash.md",
        "fetched_at": null
      }
    },
    {
      "engine": "sglang",
      "checkpoint": "root",
      "engine_version": null,
      "image": "lmsysorg/sglang:latest",
      "argv": [
        "sglang",
        "serve",
        "--model-path",
        "zai-org/GLM-5.3-Flash",
        "--tp-size",
        "4",
        "--attention-backend",
        "dsa",
        "--dsa-prefill-backend",
        "tilelang",
        "--dsa-decode-backend",
        "tilelang",
        "--linear-attn-backend",
        "triton",
        "--kv-cache-dtype",
        "bfloat16",
        "--quantization",
        "fp8",
        "--moe-runner-backend",
        "flashinfer_trtllm",
        "--max-running-requests",
        "64",
        "--chunked-prefill-size",
        "8192",
        "--max-prefill-tokens",
        "8192",
        "--disable-prefill-cuda-graph",
        "--speculative-algorithm",
        "EAGLE",
        "--speculative-num-steps",
        "3",
        "--speculative-eagle-topk",
        "1",
        "--speculative-num-draft-tokens",
        "4",
        "--language-only",
        "--encoder-urls",
        "http://localhost:30001",
        "--mem-fraction-static",
        "0.78",
        "--host",
        "0.0.0.0",
        "--port",
        "30000"
      ],
      "command": "sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --attention-backend dsa --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --linear-attn-backend triton --kv-cache-dtype bfloat16 --quantization fp8 --moe-runner-backend flashinfer_trtllm --max-running-requests 64 --chunked-prefill-size 8192 --max-prefill-tokens 8192 --disable-prefill-cuda-graph --speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --language-only --encoder-urls http://localhost:30001 --mem-fraction-static 0.78 --host 0.0.0.0 --port 30000",
      "env": {},
      "validated_hardware": [],
      "notes": null,
      "source": {
        "kind": "sglang-cookbook",
        "url": "https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.3-Flash.md",
        "fetched_at": null
      }
    },
    {
      "engine": "sglang",
      "checkpoint": "root",
      "engine_version": null,
      "image": "lmsysorg/sglang:latest",
      "argv": [
        "sglang",
        "serve",
        "--model-path",
        "zai-org/GLM-5.3-Flash",
        "--tp-size",
        "4",
        "--attn-cp-size",
        "4",
        "--enable-prefill-cp",
        "--cp-strategy",
        "interleave",
        "--moe-dense-tp-size",
        "4",
        "--ep-size",
        "1",
        "--speculative-algorithm",
        "EAGLE",
        "--speculative-num-steps",
        "5",
        "--speculative-eagle-topk",
        "1",
        "--speculative-num-draft-tokens",
        "6",
        "--dsa-prefill-backend",
        "trtllm",
        "--dsa-decode-backend",
        "trtllm",
        "--kv-cache-dtype",
        "fp8_e4m3",
        "--moe-runner-backend",
        "flashinfer_trtllm",
        "--reasoning-parser",
        "auto",
        "--tool-call-parser",
        "auto",
        "--host",
        "0.0.0.0",
        "--port",
        "30000"
      ],
      "command": "sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --attn-cp-size 4 --enable-prefill-cp --cp-strategy interleave --moe-dense-tp-size 4 --ep-size 1 --speculative-algorithm EAGLE --speculative-num-steps 5 --speculative-eagle-topk 1 --speculative-num-draft-tokens 6 --dsa-prefill-backend trtllm --dsa-decode-backend trtllm --kv-cache-dtype fp8_e4m3 --moe-runner-backend flashinfer_trtllm --reasoning-parser auto --tool-call-parser auto --host 0.0.0.0 --port 30000",
      "env": {},
      "validated_hardware": [],
      "notes": null,
      "source": {
        "kind": "sglang-cookbook",
        "url": "https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.3-Flash.md",
        "fetched_at": null
      }
    },
    {
      "engine": "sglang",
      "checkpoint": "root",
      "engine_version": null,
      "image": "lmsysorg/sglang:latest",
      "argv": [
        "sglang",
        "serve",
        "--model-path",
        "zai-org/GLM-5.3-Flash",
        "--tp-size",
        "2",
        "--dsa-prefill-backend",
        "tilelang",
        "--dsa-decode-backend",
        "tilelang",
        "--kv-cache-dtype",
        "bfloat16",
        "--moe-runner-backend",
        "triton",
        "--disaggregation-mode",
        "prefill",
        "--disaggregation-bootstrap-port",
        "8998",
        "--disaggregation-transfer-backend",
        "nixl",
        "--host",
        "0.0.0.0",
        "--port",
        "31000"
      ],
      "command": "sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 2 --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --kv-cache-dtype bfloat16 --moe-runner-backend triton --disaggregation-mode prefill --disaggregation-bootstrap-port 8998 --disaggregation-transfer-backend nixl --host 0.0.0.0 --port 31000",
      "env": {},
      "validated_hardware": [],
      "notes": null,
      "source": {
        "kind": "sglang-cookbook",
        "url": "https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.3-Flash.md",
        "fetched_at": null
      }
    },
    {
      "engine": "sglang",
      "checkpoint": "root",
      "engine_version": null,
      "image": "lmsysorg/sglang:latest",
      "argv": [
        "sglang",
        "serve",
        "--model-path",
        "zai-org/GLM-5.3-Flash",
        "--tp-size",
        "2",
        "--base-gpu-id",
        "2",
        "--dsa-prefill-backend",
        "tilelang",
        "--dsa-decode-backend",
        "tilelang",
        "--kv-cache-dtype",
        "bfloat16",
        "--moe-runner-backend",
        "triton",
        "--disaggregation-mode",
        "decode",
        "--disaggregation-transfer-backend",
        "nixl",
        "--host",
        "0.0.0.0",
        "--port",
        "32000"
      ],
      "command": "sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 2 --base-gpu-id 2 --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --kv-cache-dtype bfloat16 --moe-runner-backend triton --disaggregation-mode decode --disaggregation-transfer-backend nixl --host 0.0.0.0 --port 32000",
      "env": {},
      "validated_hardware": [],
      "notes": null,
      "source": {
        "kind": "sglang-cookbook",
        "url": "https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.3-Flash.md",
        "fetched_at": null
      }
    },
    {
      "engine": "sglang",
      "checkpoint": "root",
      "engine_version": null,
      "image": "lmsysorg/sglang:latest",
      "argv": [
        "python",
        "-m",
        "sglang_router.launch_router",
        "--pd-disaggregation",
        "--mini-lb",
        "--prefill",
        "http://127.0.0.1:31000",
        "8998",
        "--decode",
        "http://127.0.0.1:32000",
        "--host",
        "0.0.0.0",
        "--port",
        "30000"
      ],
      "command": "python -m sglang_router.launch_router --pd-disaggregation --mini-lb --prefill http://127.0.0.1:31000 8998 --decode http://127.0.0.1:32000 --host 0.0.0.0 --port 30000",
      "env": {},
      "validated_hardware": [],
      "notes": null,
      "source": {
        "kind": "sglang-cookbook",
        "url": "https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.3-Flash.md",
        "fetched_at": null
      }
    }
  ],
  "hardware": {
    "gpu_models": [
      "b200",
      "gb200",
      "h100",
      "mi355x"
    ],
    "gpu_arch": [
      "blackwell",
      "cdna4",
      "hopper"
    ],
    "min_gpus": 8,
    "tp_rule": "widest published TP is 8",
    "min_vram_per_gpu_gib": null,
    "min_total_vram_gib": null,
    "min_disk_gib": 417,
    "min_host_ram_gib": null,
    "interconnect": null,
    "cuda_min": null,
    "driver_min": null,
    "context_tokens": null
  },
  "performance": "https://onefrontier.ai/zai-org/GLM-5.3-Flash/performance",
  "evidence": [
    {
      "kind": "hf-api",
      "url": "https://huggingface.co/api/models/zai-org/GLM-5.3-Flash",
      "fetched_at": null
    },
    {
      "kind": "vllm-recipes",
      "url": "https://recipes.vllm.ai/zai-org/GLM-5.3-Flash.json",
      "fetched_at": null
    },
    {
      "kind": "sglang-cookbook",
      "url": "https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.3-Flash.md",
      "fetched_at": null
    }
  ],
  "gaps": [
    {
      "field": "hardware.npu",
      "why": "recipes name non-GPU accelerators too: ascend_950pr_8x (not carded)"
    }
  ],
  "captured_at": "2026-10-31T17:28:28Z",
  "captured_by": "hf-api + vllm-recipes + sglang-cookbook"
}