{
 "id": "lium-h200-jackson-qwen3-8b-bf16-vllm",
 "status": "published",
 "title": "Qwen3-8B BF16 on 1× H200 (Lium, Jackson) with vLLM 0.33.0",
 "published": "2026-11-10",
 "summary": "Quick-mode measurement on a Lium Secure-tier marketplace node (f092246d, Jackson, United States), 2026-11-10, default vLLM settings, $5.30 per GPU-hour (the host's listed price). Same model, workload and latency target as our other Qwen3-8B reports; the node ran tokenwatt-check first (700 W power limit, its default; 668 TFLOPS BF16; 4.30 TB/s copy bandwidth). $0.37 per million output tokens at that price. Lium provided the credit for this run and checked the node details before publication. Energy is GPU board power.",
 "hardware": {
  "vendor": "NVIDIA",
  "accelerator": "NVIDIA H200",
  "count": 1,
  "rated_bw_tbs_per_gpu": 4.8,
  "driver": "580.159.03",
  "host": "Lium Secure-tier pod (marketplace host), node f092246d, Jackson, US"
 },
 "software": {
  "engine": "vLLM",
  "engine_version": "0.33.0",
  "kernels": "vllm/vllm-openai:v0.33.0"
 },
 "model": {
  "name": "Qwen3-8B",
  "shape": "Dense",
  "quantization": "BF16 weights, BF16 KV cache",
  "parallelism": "1 replica × TP1"
 },
 "slo": {
  "ttft_p99_ms": 2000.0,
  "tpot_p99_ms": 50.0
 },
 "workload": {
  "trace": "chat-mix-v1",
  "input_tokens": "median 1,024 · p90 4,096",
  "output_tokens": "median 256 · p90 1,024",
  "arrival": "Poisson, rate swept to SLO boundary"
 },
 "power": {
  "source": "GPU board power sum (NVIDIA)",
  "kind": "board",
  "sampling_hz": 1,
  "window": "120 s steady state"
 },
 "accuracy": {
  "suite": "gsm8k-5shot",
  "threshold_pts": 1.0
 },
 "runs": 2,
 "variance_band_pct": 1.4,
 "fleet": {
  "cards": 64
 },
 "configs": [
  {
   "key": "other",
   "label": "lium-f092246d-qwen3-8b",
   "engine": "vLLM 0.33.0 · KV BF16",
   "mbu_pct": 40.5,
   "node_power_kw": 0.692,
   "goodput_tok_s": 4013.9,
   "ttft_p99_ms": 417.0,
   "tpot_p99_ms": 36.9,
   "slo_pass_count": 2,
   "repeats": 2,
   "throttle_counts": {
    "sw_power_cap": 240
   },
   "accuracy": {
    "score": 92.0,
    "delta_pts": 0.0,
    "spread_pts": 0.0
   }
  }
 ],
 "not_covered": [
  "Whole-node power (no BMC access on this host)",
  "Context lengths beyond the chat-mix-v1 trace",
  "Quick mode: short windows, few repeats — validation only, not for publishing"
 ],
 "reproduce": "tokenwatt run --spec lambda-qwen3-8b-tp1-dp1.spec.yaml --label 'lium-f092246d-qwen3-8b' --role other --out runs/lium-f092246d-qwen3-8b.json\n\ntokenwatt report runs/lium-f092246d-qwen3-8b.json --title 'Qwen3-8B BF16 on 1× H200 (Lium, Jackson) with vLLM 0.33.0'",
 "spec": {
  "name": "lambda-qwen3-8b-tp1-dp1",
  "hardware": {
   "adapter": "nvidia",
   "rated_bw_tbs_per_gpu": null,
   "gpus": null,
   "host": "Lium Secure-tier pod (marketplace host), node f092246d, Jackson, US"
  },
  "engine": {
   "endpoint": "http://127.0.0.1:8000/v1",
   "name": "vLLM",
   "version": "0.33.0",
   "kernels": "vllm/vllm-openai:v0.33.0",
   "api": "completions",
   "model": "Qwen/Qwen3-8B",
   "ignore_eos": true,
   "api_key_env": null,
   "extra_body": {}
  },
  "model": {
   "name": "Qwen3-8B",
   "config": "/root/tokenwatt-bench/models/Qwen__Qwen3-8B/config.json",
   "weight_dtype": "bf16",
   "kv_dtype": "bf16",
   "quantization": "",
   "replicas": 1,
   "tensor_parallel": 1,
   "vocab_size": 151936,
   "geometry": {}
  },
  "slo": {
   "ttft_p99_ms": 2000.0,
   "tpot_p99_ms": 50.0
  },
  "workload": {
   "trace": "chat-mix-v1",
   "input_tokens": null,
   "output_tokens": null,
   "seed": 0,
   "shared_prefix": 0.0,
   "prefix_pool": 1
  },
  "measurement": {
   "warmup_s": 45,
   "window_s": 120,
   "search_window_s": 60,
   "repeats": 2,
   "request_timeout_s": 300,
   "max_concurrency": 8192
  },
  "sweep": {
   "rates": null,
   "start_rps": 1.0,
   "growth": 1.6,
   "max_rps": 2000,
   "bisect_steps": 3,
   "backoff": 0.9,
   "max_backoffs": 4,
   "confirm": "backoff",
   "floor_rps": null,
   "confirm_steps": 5
  },
  "accuracy": {
   "suite": "/root/tokenwatt-bench/suites/gsm8k-200.jsonl",
   "name": "gsm8k-5shot",
   "scorer": "numeric",
   "max_drop_pts": 1.0,
   "seeds": 1,
   "max_tokens": 384,
   "stop": [
    "\n\nQuestion:"
   ],
   "concurrency": 32,
   "limit": 50
  },
  "power": {
   "source": "board",
   "sampling_hz": 1,
   "url": null,
   "username": null,
   "password_env": null,
   "verify_tls": false,
   "chassis": null,
   "host": null,
   "command": null,
   "field": null
  },
  "not_covered": [
   "Whole-node power (no BMC access on this host)",
   "Context lengths beyond the chat-mix-v1 trace",
   "Quick mode: short windows, few repeats — validation only, not for publishing"
  ]
 }
}