{
  "kind": "instance-env-receipt",
  "box_class": "gpu-5090-laptop-24g",
  "target_uuid": "GPU-edff232c-7dbf-2bac-07fb-921a7c9eecff",
  "written_utc": "2026-09-22T00:19:43Z",
  "unit": "bench-5090laptop-one",
  "shape": "one",
  "port": 11470,
  "base_url": "http://127.0.0.1:11470",
  "cuda_visible_devices": "GPU-edff232c-7dbf-2bac-07fb-921a7c9eecff",
  "OLLAMA_FLASH_ATTENTION": "1",
  "OLLAMA_KV_CACHE_TYPE": "f16",
  "OLLAMA_CONTEXT_LENGTH": 32768,
  "OLLAMA_<parallel-requests>": 1,
  "OLLAMA_MAX_LOADED_MODELS": 1,
  "OLLAMA_KEEP_ALIVE": "0 (the server default; every bench request sends its own keep_alive, which wins, and every arm unloads on the way out)",
  "models_dir": "/usr/share/ollama/.ollama/models",
  "models_dir_writable_by_this_user": false,
  "api_version": {
    "version": "0.32.13"
  },
  "ollama_binary": "/workshop/bench-laptop-5090-2026-09-21/ollama-0.32.13/bin/ollama",
  "ollama_client_version": "0.32.13",
  "ollama_version_pin": "0.32.13",
  "disclosed_tenants": "nomic-embed-text:latest on the SYSTEM ollama (:<the runtime's default port>, OLLAMA_KEEP_ALIVE=-1, ~323 MB VRAM) \u2014 disclosed, never unloaded",
  "power_and_clocks_at_start_csv": "[N/A], 150.00 W, 95.00 W, 175.00 W, 1657 MHz, 14001 MHz, 3090 MHz",
  "power_and_clocks_at_start_fields": "power.limit,enforced.power.limit,power.default_limit,power.max_limit,clocks.sm,clocks.mem,clocks.max.sm",
  "nvidia_powerd_at_start": "active",
  "clock_lock_unit_at_start": "active",
  "clock_lock_unit_name": "ai-perf.service",
  "clock_lock_range_declared": "1200,2550",
  "clock_lock_unit_state_is_not_evidence": "ai-perf.service is Type=oneshot and reads 'active (exited)' for the whole uptime whatever happens to the card afterwards. The lock's real state is read from the CARD (clocks.sm against the lock's floor) and is recorded in this leg's clock-lock receipt.",
  "power_limits_at_start_w": "0, [N/A], 150.00 W;",
  "persistence_mode_at_start": "0, Enabled;",
  "pcie_link_width_at_start": "0, 8;"
}