{
 "schema": "local-ai-bench/result/v1",
 "run_id": "20261003T143733Z-ik_llama-glm-5.3-flash-iq2-m-128k-1x-gpu2-ttft",
 "ticket": "T22b",
 "kind": "ttft",
 "model": "glm-5.3-flash",
 "config_id": "ik_llama-glm-5.3-flash-iq2-m-128k-1x-gpu2",
 "outcome": "pass",
 "failed_stage": null,
 "exit_status": 0,
 "started_at": "2026-10-03T14:37:33.561498+00:00",
 "finished_at": "2026-10-03T14:51:06.543652+00:00",
 "launch": {
  "file": "launches/ik_llama-glm-5.3-flash-iq2-m-128k-1x.json",
  "sha256": "168e8b490c871dcebe6afed1dfd973be9985379eb748e37f17be98b86a86e44e",
  "image": "local-ai-bench/ik-llama-cuda@sha256:d30fa2796c72509c9158a6202fed46c8ce159f3344f3735120be65a73a8137b1",
  "argv": [
   "/app/llama-server",
   "--model",
   "/models/GLM-5.3-Flash-BF16-IQ2_M/GLM-5.3-Flash-BF16-IQ2_M-00001-of-00004.gguf",
   "--ctx-size",
   "131072",
   "--flash-attn",
   "on",
   "--mla-use",
   "3",
   "--dsa",
   "--cache-type-k",
   "q8_0",
   "--n-gpu-layers",
   "999",
   "--cpu-moe",
   "--batch-size",
   "2048",
   "--ubatch-size",
   "2048",
   "--parallel",
   "1",
   "--threads",
   "16",
   "--jinja",
   "--metrics",
   "--host",
   "0.0.0.0",
   "--port",
   "8080"
  ],
  "env": {
   "CUDA_DEVICE_ORDER": "PCI_BUS_ID"
  },
  "engine": "ik_llama.cpp",
  "engine_source_commit": "https://github.com/ikawrakow/ik_llama.cpp/tree/5bf8f0fe4db98e9560de0f495232f8d3a733c678",
  "mtp": null,
  "entrypoint": "/app/llama-server",
  "port": 8080,
  "shm": "16g",
  "flags": [],
  "weights_at": [
   "/models"
  ]
 },
 "weights": [
  {
   "repo": "bartowski/GLM-5.3-Flash-BF16-GGUF",
   "revision": "66e5e9f0e337470e8801b99bae6c45779b042cc2",
   "manifest": "models/bartowski-GLM-5.3-Flash-IQ2_M.json"
  }
 ],
 "host": {
  "hostname": "omarchy-gpu",
  "cpu": "AMD Ryzen 9 5950X 16-Core Processor",
  "ram_total_gib": 125.7,
  "ram_layout": "DIMM_A1 32 GiB DDR4 3200 MT/s, DIMM_A2 32 GiB DDR4 3200 MT/s, DIMM_B1 32 GiB DDR4 3200 MT/s, DIMM_B2 32 GiB DDR4 3200 MT/s (AM4: 2 channels)",
  "kernel": "7.2.5-3-omarchy",
  "driver": "610.57.04",
  "cuda": "13.3",
  "cpus_online": "0-31",
  "cpus_offline": "none",
  "machine_checks_this_boot": 0
 },
 "gpus": [
  {
   "index": 0,
   "uuid": "GPU-816b43e4-8d65-dfd7-2234-8517b3dfbf2d",
   "name": "NVIDIA GeForce RTX 3090",
   "bus_id": "00000000:04:00.0",
   "pcie_gen_max": 4,
   "pcie_width": 8,
   "display_active": false,
   "used_by_run": false
  },
  {
   "index": 1,
   "uuid": "GPU-c67ac872-3371-a88c-aa92-d969daf6405e",
   "name": "NVIDIA GeForce RTX 3090",
   "bus_id": "00000000:0B:00.0",
   "pcie_gen_max": 4,
   "pcie_width": 8,
   "display_active": true,
   "used_by_run": false
  },
  {
   "index": 2,
   "uuid": "GPU-76d3c6af-7f18-69d2-3145-899103de1722",
   "name": "NVIDIA GeForce RTX 3090",
   "bus_id": "00000000:0C:00.0",
   "pcie_gen_max": 4,
   "pcie_width": 8,
   "display_active": false,
   "used_by_run": true
  }
 ],
 "layout": {
  "name": "current",
  "cards": 1,
  "display": "on"
 },
 "context": {
  "configured": 131072,
  "occupied_max": {
   "state": "unavailable",
   "reason": "no occupancy measured in this run"
  },
  "headroom_min": {
   "state": "unavailable",
   "reason": "no occupancy measured in this run"
  }
 },
 "cache_state": {
  "cold": false,
  "reset": []
 },
 "provenance": {
  "bench_commit": "57320e8fbf776bca99fc63e2de1647d22ef83f06",
  "bench_dirty": false,
  "pins_sha256": "858564b6e07125ac48c2ef6c5178d0a53596f21eb5f0ebda43906472b01b4d78",
  "registry_commit": "d21258dd744e7c78be28177c90060c6af8e10b7e",
  "kit_commit": "ef883d269e50ecbea290f919f095e2f3ca633b42",
  "harness_commit": "04d809ceab9df28f9adaed044884180159172930"
 },
 "metrics": {
  "ttft_prefill_8k_tps": {
   "value": 203.1,
   "unit": "tok/s",
   "detail": {
    "prompt_tokens": [
     10751,
     10785,
     10716
    ],
    "ttft_s": [
     52.615,
     53.39,
     52.749
    ]
   }
  },
  "ttft_prefill_32k_tps": {
   "value": 196.7,
   "unit": "tok/s",
   "detail": {
    "prompt_tokens": [
     42739,
     42927,
     42933
    ],
    "ttft_s": [
     217.584,
     218.259,
     218.191
    ]
   }
  },
  "ttft_prefill_tps": {
   "value": 203.1,
   "unit": "tok/s",
   "detail": {
    "prompt_tokens": [
     10751,
     10785,
     10716
    ],
    "ttft_s": [
     52.615,
     53.39,
     52.749
    ]
   }
  }
 },
 "eligibility": "none",
 "artifacts": [
  "artifacts/runs/20261003T143733Z-lab-ik_llama-glm-5.3-flash-iq2-m-128k-1x-gpu2-ttft"
 ],
 "notes": "headline length 8192; prompts carry random nonces"
}