{
 "arm": "L-IQ3-ub",
 "phase": "speed",
 "attempt": 1,
 "engine": "llama.cpp",
 "quant": "IQ3_S",
 "run_dir": "/workshop/bench-archive/plans-2026-10-02/strata-bench/records/L-IQ3-ub/speed/a1",
 "port": "withheld-2026-10-13",
 "server_argv": [
  "/data/strata-bench/build/llama.cpp-3cf03257/bin/llama-server",
  "-m",
  "/data/strata-bench/models/ISTA-ed59f920/IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf",
  "--host",
  "127.0.0.1",
  "--port",
  "withheld-2026-10-13",
  "-ngl",
  "99",
  "--n-cpu-moe",
  "42",
  "-c",
  "131072",
  "-b",
  "4096",
  "-ub",
  "4096",
  "-fa",
  "on",
  "-ctk",
  "q8_0",
  "-ctv",
  "q8_0",
  "-lm",
  "mmap",
  "--lazy-mode",
  "on",
  "-fit",
  "off",
  "-np",
  "1",
  "--cache-ram",
  "0",
  "--no-webui",
  "--jinja",
  "-lv",
  "4",
  "-t",
  "8",
  "-tb",
  "8"
 ],
 "server_env": {},
 "key_env": "LLAMA_API_KEY",
 "server_cwd": null,
 "strata_engine_log": null,
 "slices_path": "/workshop/bench-archive/plans-2026-10-02/strata-bench/records/SLICES.json",
 "contexts": [
  "4K",
  "32K",
  "128K"
 ],
 "repeats": 3,
 "max_tokens": 256,
 "health_timeout_s": 1200.0,
 "request_timeout_s": 2400.0,
 "egress_mode": "netns",
 "model_name": "qwen3.8-flash-next-iq3_s",
 "expect_commit": "3cf03257f219afbe7334045ff7c6a06ac68c627d"
}