{
  "model_id": "m6",
  "model_tag": "nemotron-3.5-lightning:30b-a3b",
  "box_class": "cpu-laptop",
  "started_utc": "2026-08-25T17:09:09Z",
  "nproc": 24,
  "num_predict": 256,
  "prompt_sha256": "90eedd0c53f9554ae3837674504fcb7090013d9a432a653352183c0f25a7ce5c",
  "nvidia_before": "0, 15 MiB, 0 %",
  "ollama_version": "0.32.15",
  "runs": [
    {
      "ttft_ms": 178.09,
      "first_token_was_thinking": false,
      "wall_s": 16.7918,
      "eval_count": 256,
      "eval_duration_ns": 16612554000,
      "decode_tok_s": 15.41,
      "prompt_eval_count": 532,
      "prompt_eval_duration_ns": 175136000,
      "prefill_tok_s": 3037.639,
      "load_duration_ns": 407716,
      "total_duration_ns": 16790147764,
      "streamed_chunks": 245,
      "response_chars": 1029,
      "thinking_chars": 0,
      "done_reason": "length",
      "run": 1
    },
    {
      "ttft_ms": 178.2,
      "first_token_was_thinking": false,
      "wall_s": 16.8533,
      "eval_count": 256,
      "eval_duration_ns": 16673945000,
      "decode_tok_s": 15.353,
      "prompt_eval_count": 532,
      "prompt_eval_duration_ns": 174222000,
      "prefill_tok_s": 3053.575,
      "load_duration_ns": 771177,
      "total_duration_ns": 16851533030,
      "streamed_chunks": 245,
      "response_chars": 1029,
      "thinking_chars": 0,
      "done_reason": "length",
      "run": 2
    },
    {
      "ttft_ms": 179.15,
      "first_token_was_thinking": false,
      "wall_s": 16.8575,
      "eval_count": 256,
      "eval_duration_ns": 16677387999,
      "decode_tok_s": 15.35,
      "prompt_eval_count": 532,
      "prompt_eval_duration_ns": 175789000,
      "prefill_tok_s": 3026.355,
      "load_duration_ns": 439898,
      "total_duration_ns": 16856047412,
      "streamed_chunks": 245,
      "response_chars": 1029,
      "thinking_chars": 0,
      "done_reason": "length",
      "run": 3
    },
    {
      "ttft_ms": 179.25,
      "first_token_was_thinking": false,
      "wall_s": 16.8631,
      "eval_count": 256,
      "eval_duration_ns": 16682877000,
      "decode_tok_s": 15.345,
      "prompt_eval_count": 532,
      "prompt_eval_duration_ns": 175954000,
      "prefill_tok_s": 3023.518,
      "load_duration_ns": 628728,
      "total_duration_ns": 16861422131,
      "streamed_chunks": 245,
      "response_chars": 1029,
      "thinking_chars": 0,
      "done_reason": "length",
      "run": 4
    },
    {
      "ttft_ms": 179.75,
      "first_token_was_thinking": false,
      "wall_s": 16.8934,
      "eval_count": 256,
      "eval_duration_ns": 16712433000,
      "decode_tok_s": 15.318,
      "prompt_eval_count": 532,
      "prompt_eval_duration_ns": 176174000,
      "prefill_tok_s": 3019.742,
      "load_duration_ns": 690616,
      "total_duration_ns": 16891757202,
      "streamed_chunks": 245,
      "response_chars": 1029,
      "thinking_chars": 0,
      "done_reason": "length",
      "run": 5
    }
  ],
  "errors": [],
  "quantization": "Q4_K_M",
  "param_size": "32.9B",
  "family": "nemotron_h_moe",
  "context_length": 1048576,
  "think_mode": false,
  "think_note": "think:false accepted",
  "warmup_discarded": {
    "ttft_ms": 177.95,
    "first_token_was_thinking": false,
    "wall_s": 16.6515,
    "eval_count": 256,
    "eval_duration_ns": 16471273000,
    "decode_tok_s": 15.542,
    "prompt_eval_count": 532,
    "prompt_eval_duration_ns": 174609000,
    "prefill_tok_s": 3046.807,
    "load_duration_ns": 573717,
    "total_duration_ns": 16648724860,
    "streamed_chunks": 245,
    "response_chars": 1029,
    "thinking_chars": 0,
    "done_reason": "length"
  },
  "ps_after_load": [
    {
      "name": "nemotron-3.5-lightning:30b-a3b",
      "model": "nemotron-3.5-lightning:30b-a3b",
      "size": 25609340188,
      "digest": "e7a64ff15fb174c42b4f463e5c888c4f2c7b9cabf9e8d65a1c0874405426c1b2",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "nemotron_h_moe",
        "families": [
          "nemotron_h_moe"
        ],
        "parameter_size": "32.9B",
        "quantization_level": "Q4_K_M"
      },
      "expires_at": "2026-08-25T17:19:46.624117344Z",
      "size_vram": 0,
      "context_length": 4096
    }
  ],
  "size_vram": 0,
  "size_total": 25609340188,
  "cpu_only_receipt": true,
  "peak_runner_rss_kb": 25342368,
  "peak_runner_rss_gib": 24.17,
  "peak_runner_threads": 34,
  "rss_samples": 165,
  "loadavg_during_runs": {
    "min": 2.11,
    "median": 3.78,
    "max": 4.41,
    "mean": 3.45,
    "samples": 165,
    "nproc": 24
  },
  "contention_suspected": false,
  "contention_note": "loadavg consistent with this bench owning the machine",
  "foreign_gpu_procs_during": "0, 15 MiB, 0 %",
  "derived": {
    "decode_tok_s": {
      "min": 15.318,
      "median": 15.35,
      "max": 15.41,
      "mean": 15.355,
      "n": 5
    },
    "ttft_ms": {
      "min": 178.09,
      "median": 179.15,
      "max": 179.75,
      "mean": 178.888,
      "n": 5
    },
    "wall_s": {
      "min": 16.7918,
      "median": 16.8575,
      "max": 16.8934,
      "mean": 16.852,
      "n": 5
    },
    "prefill_tok_s": {
      "min": 3019.742,
      "median": 3026.355,
      "max": 3053.575,
      "mean": 3032.166,
      "n": 5
    },
    "eval_count": {
      "min": 256,
      "median": 256,
      "max": 256,
      "mean": 256.0,
      "n": 5
    }
  },
  "cold_load": [
    {
      "ttft_ms": 20895.44,
      "first_token_was_thinking": false,
      "wall_s": 20.8965,
      "eval_count": 1,
      "eval_duration_ns": 1000,
      "decode_tok_s": 1000000.0,
      "prompt_eval_count": 532,
      "prompt_eval_duration_ns": 9802587000,
      "prefill_tok_s": 54.271,
      "load_duration_ns": 11089496424,
      "total_duration_ns": 20894927273,
      "streamed_chunks": 1,
      "response_chars": 4,
      "thinking_chars": 0,
      "done_reason": "length",
      "wall_to_first_token_s": 20.8966,
      "ps_confirmed_empty_before": true,
      "load_duration_s": 11.0895
    },
    {
      "ttft_ms": 22002.98,
      "first_token_was_thinking": false,
      "wall_s": 22.0042,
      "eval_count": 1,
      "eval_duration_ns": 1000,
      "decode_tok_s": 1000000.0,
      "prompt_eval_count": 532,
      "prompt_eval_duration_ns": 9902622000,
      "prefill_tok_s": 53.723,
      "load_duration_ns": 12096758185,
      "total_duration_ns": 22002293736,
      "streamed_chunks": 1,
      "response_chars": 4,
      "thinking_chars": 0,
      "done_reason": "length",
      "wall_to_first_token_s": 22.0043,
      "ps_confirmed_empty_before": true,
      "load_duration_s": 12.0968
    }
  ],
  "cold_load_note": "PAGE-CACHE-WARM: no sudo to drop caches, so this is warm-disk reload, not a true cold read from NVMe.",
  "nvidia_after": "0, 15 MiB, 0 %",
  "ps_final": [
    {
      "name": "nemotron-3.5-lightning:30b-a3b",
      "model": "nemotron-3.5-lightning:30b-a3b",
      "size": 25609340188,
      "digest": "e7a64ff15fb174c42b4f463e5c888c4f2c7b9cabf9e8d65a1c0874405426c1b2",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "nemotron_h_moe",
        "families": [
          "nemotron_h_moe"
        ],
        "parameter_size": "32.9B",
        "quantization_level": "Q4_K_M"
      },
      "expires_at": "2026-08-25T17:21:55.498311101Z",
      "size_vram": 0,
      "context_length": 4096
    }
  ],
  "finished_utc": "2026-08-25T17:11:56Z"
}