{
  "schema_version": 1,
  "updated": "2026-09-09",
  "classification": "measured-results-only",
  "hardware": "Ciru: Ryzen AI Max+ 395, gfx1151, 128 GB unified memory, NixOS",
  "baseline": "Locally qualified v2.0.1, MTP6, b2048/u512; no separate public v2.0.1 tag.",
  "v3_profile": "v3.0.0, same weights, MTP6, b1024/u1024, F16 target KV, Q8 draft KV, one slot, context 262144.",
  "halo_profile": "Pristine 5f851647fe5ed795dfd6c0a3fba543114879e874, Vulkan, Unsloth UD-Q4_K_XL target, EasiiX Q8 head, MTP3, native defaults.",
  "serving": {
    "Previous CIRU": {
      "4096": {
        "rows": 2,
        "PP": 392.00366125294556,
        "TG": 22.51733524535651,
        "TG_range": [
          22.05163555418191,
          23.003129150072414
        ],
        "TTFP_s": 10.69582200050354,
        "request_s": 16.336945295333862,
        "drafted": 588,
        "accepted": 156,
        "idle_ram_GiB": 100.72896957397461,
        "peak_ram_GiB": 103.4262580871582,
        "peak_GTT_GiB": 88.57872772216797,
        "peak_VRAM_GiB": 0.5218048095703125,
        "max_delta_ram_GiB": 2.1545333862304688
      },
      "65536": {
        "rows": 1,
        "PP": 284.4915510098569,
        "TG": 13.332401115050645,
        "TG_range": [
          13.332401115050644,
          13.332401115050644
        ],
        "TTFP_s": 230.45938777923584,
        "request_s": 239.98778319358826,
        "drafted": 283,
        "accepted": 79,
        "idle_ram_GiB": 100.59429168701172,
        "peak_ram_GiB": 101.31758499145508,
        "peak_GTT_GiB": 88.57872772216797,
        "peak_VRAM_GiB": 0.5173988342285156,
        "max_delta_ram_GiB": 0.7232933044433594
      }
    },
    "CIRU v3": {
      "4096": {
        "rows": 6,
        "PP": 455.6541833933926,
        "TG": 24.599275541650545,
        "TG_range": [
          23.714691718344156,
          25.19420366676837
        ],
        "TTFP_s": 9.245681206385294,
        "request_s": 14.40951939423879,
        "drafted": 1680,
        "accepted": 480,
        "idle_ram_GiB": 103.05811818440755,
        "peak_ram_GiB": 106.01566696166992,
        "peak_GTT_GiB": 90.2929458618164,
        "peak_VRAM_GiB": 0.5292892456054688,
        "max_delta_ram_GiB": 2.4259910583496094
      },
      "65536": {
        "rows": 3,
        "PP": 369.80548798995795,
        "TG": 24.219011568105987,
        "TG_range": [
          24.166916898916444,
          24.30324323910564
        ],
        "TTFP_s": 177.32060686747232,
        "request_s": 182.56692719459534,
        "drafted": 717,
        "accepted": 258,
        "idle_ram_GiB": 102.90898895263672,
        "peak_ram_GiB": 103.66057205200195,
        "peak_GTT_GiB": 90.2929458618164,
        "peak_VRAM_GiB": 0.5248832702636719,
        "max_delta_ram_GiB": 0.7370414733886719
      }
    },
    "Halo": {
      "4096": {
        "rows": 4,
        "PP": 381.49292683846284,
        "TG": 35.30120650212089,
        "TG_range": [
          34.77293274914806,
          35.57767783656343
        ],
        "TTFP_s": 11.094179451465607,
        "request_s": 14.69240266084671,
        "drafted": 528,
        "accepted": 328,
        "idle_ram_GiB": 102.4269323348999,
        "peak_ram_GiB": 104.8825912475586,
        "peak_GTT_GiB": 93.07597351074219,
        "peak_VRAM_GiB": 1.85498046875,
        "max_delta_ram_GiB": 2.7664871215820312
      },
      "65536": {
        "rows": 2,
        "PP": 263.42074609163245,
        "TG": 23.278333535262185,
        "TG_range": [
          23.22488713070601,
          23.33202649489396
        ],
        "TTFP_s": 248.91091644763947,
        "request_s": 254.3688863515854,
        "drafted": 276,
        "accepted": 160,
        "idle_ram_GiB": 103.14214324951172,
        "peak_ram_GiB": 103.72273635864258,
        "peak_GTT_GiB": 93.17262649536133,
        "peak_VRAM_GiB": 1.9886512756347656,
        "max_delta_ram_GiB": 0.597412109375
      }
    }
  },
  "optional_mtp2": {
    "4096": {
      "rows": 4,
      "PP": 453.08718324929157,
      "TG": 29.386021312616883,
      "TG_range": [
        28.85317053177984,
        29.90677798267714
      ],
      "TTFP_s": 9.292197465896606,
      "request_s": 13.615030109882355,
      "drafted": 448,
      "accepted": 284,
      "idle_ram_GiB": 102.58193302154541,
      "peak_ram_GiB": 105.33094024658203,
      "peak_GTT_GiB": 89.85221862792969,
      "peak_VRAM_GiB": 0.5273895263671875,
      "max_delta_ram_GiB": 2.2389984130859375
    },
    "65536": {
      "rows": 2,
      "PP": 373.0762034331891,
      "TG": 24.880485510349693,
      "TG_range": [
        24.87814118364711,
        24.882830278916934
      ],
      "TTFP_s": 175.76338636875153,
      "request_s": 180.8699688911438,
      "drafted": 232,
      "accepted": 136,
      "idle_ram_GiB": 102.45176124572754,
      "peak_ram_GiB": 103.16925811767578,
      "peak_GTT_GiB": 89.85221862792969,
      "peak_VRAM_GiB": 0.5229873657226562,
      "max_delta_ram_GiB": 0.7927474975585938
    }
  },
  "coding20": {
    "Previous CIRU": {
      "rows": 20,
      "PP": 148.5313314164119,
      "TG": 53.327449701233775,
      "TG_range": [
        47.918969023381464,
        57.79477805890751
      ],
      "TTFP_s": 0.811668586730957,
      "request_s": 3.774738335609436,
      "drafted": 3162,
      "accepted": 2664,
      "idle_ram_GiB": 105.73584384918213,
      "peak_ram_GiB": 108.11417388916016,
      "peak_GTT_GiB": 88.58134460449219,
      "peak_VRAM_GiB": 0.5263214111328125,
      "max_delta_ram_GiB": 0.6338348388671875,
      "generated_tokens": 3179,
      "prompt_seconds": 15.181982,
      "generation_seconds": 59.237784999999995,
      "total_request_seconds": 75.49476671218872
    },
    "CIRU v3 MTP6": {
      "rows": 20,
      "PP": 219.50646380829988,
      "TG": 53.2389694088275,
      "TG_range": [
        48.25151585152767,
        57.44670920116761
      ],
      "TTFP_s": 0.5656813144683838,
      "request_s": 3.533544683456421,
      "drafted": 3162,
      "accepted": 2664,
      "idle_ram_GiB": 107.95920333862304,
      "peak_ram_GiB": 110.46823501586914,
      "peak_GTT_GiB": 90.29296112060547,
      "peak_VRAM_GiB": 0.5336418151855469,
      "max_delta_ram_GiB": 0.4556770324707031,
      "generated_tokens": 3179,
      "prompt_seconds": 10.273046,
      "generation_seconds": 59.336235,
      "total_request_seconds": 70.67089366912842
    },
    "CIRU v3 MTP2": {
      "rows": 20,
      "PP": 226.2516078412486,
      "TG": 39.63335865299028,
      "TG_range": [
        36.41629100986472,
        41.0896075498267
      ],
      "TTFP_s": 0.5504455924034118,
      "request_s": 4.578490233421325,
      "drafted": 2180,
      "accepted": 2119,
      "idle_ram_GiB": 107.43915119171143,
      "peak_ram_GiB": 109.95774841308594,
      "peak_GTT_GiB": 89.85222625732422,
      "peak_VRAM_GiB": 0.530792236328125,
      "max_delta_ram_GiB": 0.4302635192871094,
      "generated_tokens": 3212,
      "prompt_seconds": 9.96678,
      "generation_seconds": 80.538216,
      "total_request_seconds": 91.56980466842651
    },
    "Halo MTP3": {
      "rows": 20,
      "PP": 176.1027271635372,
      "TG": 49.48345935868638,
      "TG_range": [
        46.09872313796549,
        51.46158955201079
      ],
      "TTFP_s": 0.701993727684021,
      "request_s": 3.9575579285621645,
      "drafted": 2502,
      "accepted": 2415,
      "idle_ram_GiB": 106.45168437957764,
      "peak_ram_GiB": 109.05359268188477,
      "peak_GTT_GiB": 91.11787796020508,
      "peak_VRAM_GiB": 1.8333740234375,
      "max_delta_ram_GiB": 0.5126419067382812,
      "generated_tokens": 3241,
      "prompt_seconds": 12.805026,
      "generation_seconds": 65.092458,
      "total_request_seconds": 79.15115857124329
    }
  },
  "full_capacity": {
    "input_tokens": 261888,
    "output_tokens": 128,
    "rows": 1,
    "PP": 257.4360682269633,
    "TG": 17.99524727099241,
    "TG_range": [
      17.99524727099241,
      17.99524727099241
    ],
    "TTFP_s": 1017.3788130283356,
    "request_s": 1024.442313671112,
    "drafted": 214,
    "accepted": 90,
    "idle_ram_GiB": 102.63951873779297,
    "peak_ram_GiB": 104.53916549682617,
    "peak_GTT_GiB": 90.98435974121094,
    "peak_VRAM_GiB": 0.5237464904785156,
    "max_delta_ram_GiB": 1.8996467590332031
  },
  "hard_panel": [
    {
      "profile": "Previous CIRU (v2.0.1)",
      "wall": {
        "after_ready_seconds": 1757.111019048025,
        "load_seconds": 31.165580605040304,
        "total_seconds": 1788.2766006630845
      },
      "output_tokens": 33294,
      "short": {
        "groups": {
          "ifeval": {
            "passed": 5,
            "total": 8
          },
          "gsm8k": {
            "passed": 8,
            "total": 8
          },
          "humaneval": {
            "passed": 5,
            "total": 6
          }
        },
        "whole_stage_wall_seconds": 320.33387160894927,
        "output_tokens": 8911,
        "request_wall_seconds_sum": 260.78946709632874,
        "pp_tps": 269.1525896956804,
        "tg_tps": 38.43611943974174
      },
      "long": {
        "groups": {
          "gsm8k": {
            "passed": 2,
            "total": 2,
            "generated_tokens": 956
          },
          "humaneval": {
            "passed": 2,
            "total": 4,
            "generated_tokens": 3945
          },
          "ifeval": {
            "passed": 2,
            "total": 2,
            "generated_tokens": 597
          }
        },
        "wall_seconds": 283.9170971038984,
        "generated_tokens": 5498,
        "tg_tps": 21.749810096227776
      },
      "seed_seconds": 206.33202179009095,
      "seed_input_tokens": 63000,
      "hermes": {
        "cases": 12,
        "native_full_passes": 7,
        "native_mean_points": 80.83333333333333,
        "reviewed_end_states": 11,
        "rounds": [
          {
            "round": "hermes-1",
            "wall_seconds": 352.545,
            "outcome_count": 6,
            "generated_tokens": 6933,
            "api_calls": 34,
            "native_performance": {
              "wall_seconds": 352.545,
              "completed_http_requests": 34,
              "http_errors": [],
              "generated_tokens": 6933,
              "new_prefill_tokens": 29018,
              "timed_generated_tokens": 6899,
              "request_prefill_seconds_sum": 101.74647099999997,
              "request_decode_seconds_sum": 195.91637000000003,
              "pp_new_tokens_per_s": 285.1990807622213,
              "tg_pooled_per_request_tokens_per_s": 35.21400483277635,
              "generation_tokens_per_wall_second": 19.665574607496914,
              "cache_hit_tokens": 103843,
              "definitions": "Parsed retained SSE/JSON terminal usage and native timings. PP=prompt_n/prompt_seconds; TG=sum(predicted_n-1)/decode_seconds. Actual round wall includes tools and verifier work. No generation repeated."
            },
            "reviewed_outcome_count": 6
          },
          {
            "round": "hermes-2",
            "wall_seconds": 395.462,
            "outcome_count": 4,
            "generated_tokens": 8963,
            "api_calls": 37,
            "native_performance": {
              "wall_seconds": 395.462,
              "completed_http_requests": 37,
              "http_errors": [],
              "generated_tokens": 8963,
              "new_prefill_tokens": 23018,
              "timed_generated_tokens": 8926,
              "request_prefill_seconds_sum": 87.02983600000002,
              "request_decode_seconds_sum": 250.60983700000006,
              "pp_new_tokens_per_s": 264.48400982853735,
              "tg_pooled_per_request_tokens_per_s": 35.6171174557685,
              "generation_tokens_per_wall_second": 22.664630229958885,
              "cache_hit_tokens": 129379,
              "definitions": "Parsed retained SSE/JSON terminal usage and native timings. PP=prompt_n/prompt_seconds; TG=sum(predicted_n-1)/decode_seconds. Actual round wall includes tools and verifier work. No generation repeated."
            },
            "reviewed_outcome_count": 5
          }
        ]
      },
      "health": [
        {
          "label": "health-C1",
          "wall_seconds": 38.401602292084135,
          "generated_tokens": 1640,
          "total": 10,
          "base_pass": 10,
          "plus_pass": 10
        },
        {
          "label": "long-health-C1",
          "wall_seconds": 61.90521405194886,
          "generated_tokens": 1332,
          "total": 8,
          "base_pass": 8,
          "plus_pass": 8
        }
      ]
    },
    {
      "profile": "CIRU v3",
      "wall": {
        "after_ready_seconds": 1518.3177031480009,
        "load_seconds": 31.14865791995544,
        "total_seconds": 1549.4663619579514
      },
      "output_tokens": 33451,
      "short": {
        "groups": {
          "ifeval": {
            "passed": 5,
            "total": 8
          },
          "gsm8k": {
            "passed": 8,
            "total": 8
          },
          "humaneval": {
            "passed": 5,
            "total": 6
          }
        },
        "whole_stage_wall_seconds": 320.8469852799317,
        "output_tokens": 9311,
        "request_wall_seconds_sum": 260.453138589859,
        "pp_tps": 350.3353163709068,
        "tg_tps": 39.09385075023305
      },
      "long": {
        "groups": {
          "gsm8k": {
            "passed": 2,
            "total": 2,
            "generated_tokens": 920
          },
          "humaneval": {
            "passed": 2,
            "total": 4,
            "generated_tokens": 3573
          },
          "ifeval": {
            "passed": 2,
            "total": 2,
            "generated_tokens": 597
          }
        },
        "wall_seconds": 161.89970062102657,
        "generated_tokens": 5090,
        "tg_tps": 35.93143891173188
      },
      "seed_seconds": 162.79952381795738,
      "seed_input_tokens": 63000,
      "hermes": {
        "cases": 12,
        "native_full_passes": 11,
        "native_mean_points": 95.83333333333333,
        "reviewed_end_states": 12,
        "rounds": [
          {
            "round": "hermes-1",
            "wall_seconds": 381.558,
            "outcome_count": 6,
            "generated_tokens": 8814,
            "api_calls": 34,
            "native_performance": {
              "wall_seconds": 381.558,
              "completed_http_requests": 34,
              "http_errors": [],
              "generated_tokens": 8814,
              "new_prefill_tokens": 32229,
              "timed_generated_tokens": 8780,
              "request_prefill_seconds_sum": 85.868804,
              "request_decode_seconds_sum": 238.09672100000003,
              "pp_new_tokens_per_s": 375.3283905060562,
              "tg_pooled_per_request_tokens_per_s": 36.87577033032722,
              "generation_tokens_per_wall_second": 23.100026732502005,
              "cache_hit_tokens": 97854,
              "definitions": "Parsed retained SSE/JSON terminal usage and native timings. PP=prompt_n/prompt_seconds; TG=sum(predicted_n-1)/decode_seconds. Actual round wall includes tools and verifier work. No generation repeated."
            },
            "reviewed_outcome_count": 6
          },
          {
            "round": "hermes-2",
            "wall_seconds": 316.008,
            "outcome_count": 6,
            "generated_tokens": 7246,
            "api_calls": 33,
            "native_performance": {
              "wall_seconds": 316.008,
              "completed_http_requests": 33,
              "http_errors": [],
              "generated_tokens": 7246,
              "new_prefill_tokens": 23730,
              "timed_generated_tokens": 7213,
              "request_prefill_seconds_sum": 65.12937900000001,
              "request_decode_seconds_sum": 192.581227,
              "pp_new_tokens_per_s": 364.35170063574526,
              "tg_pooled_per_request_tokens_per_s": 37.454325701227354,
              "generation_tokens_per_wall_second": 22.929799245588722,
              "cache_hit_tokens": 100868,
              "definitions": "Parsed retained SSE/JSON terminal usage and native timings. PP=prompt_n/prompt_seconds; TG=sum(predicted_n-1)/decode_seconds. Actual round wall includes tools and verifier work. No generation repeated."
            },
            "reviewed_outcome_count": 6
          }
        ]
      },
      "health": [
        {
          "label": "health-C1",
          "wall_seconds": 36.41694383090362,
          "generated_tokens": 1640,
          "total": 10,
          "base_pass": 10,
          "plus_pass": 10
        },
        {
          "label": "long-health-C1",
          "wall_seconds": 40.67496939992998,
          "generated_tokens": 1333,
          "total": 8,
          "base_pass": 8,
          "plus_pass": 8
        }
      ]
    },
    {
      "profile": "Halo MTP3",
      "wall": {
        "after_ready_seconds": 1474.4292242299998,
        "load_seconds": 33.61671800306067,
        "total_seconds": 1508.0459434330696
      },
      "output_tokens": 31058,
      "short": {
        "groups": {
          "ifeval": {
            "passed": 6,
            "total": 8
          },
          "gsm8k": {
            "passed": 8,
            "total": 8
          },
          "humaneval": {
            "passed": 5,
            "total": 6
          }
        },
        "whole_stage_wall_seconds": 275.59877648192924,
        "output_tokens": 8255,
        "request_wall_seconds_sum": 216.36825466156006,
        "pp_tps": 272.613431910844,
        "tg_tps": 43.97370591373599
      },
      "long": {
        "groups": {
          "gsm8k": {
            "passed": 2,
            "total": 2,
            "generated_tokens": 889
          },
          "humaneval": {
            "passed": 3,
            "total": 4,
            "generated_tokens": 4156
          },
          "ifeval": {
            "passed": 2,
            "total": 2,
            "generated_tokens": 672
          }
        },
        "wall_seconds": 202.96475215093233,
        "generated_tokens": 5717,
        "tg_tps": 31.245162582225024
      },
      "seed_seconds": 201.0019980610814,
      "seed_input_tokens": 63000,
      "hermes": {
        "cases": 12,
        "native_full_passes": 11,
        "native_mean_points": 95.83333333333333,
        "reviewed_end_states": 12,
        "rounds": [
          {
            "round": "hermes-1",
            "wall_seconds": 307.739,
            "outcome_count": 6,
            "generated_tokens": 6705,
            "api_calls": 36,
            "native_performance": {
              "wall_seconds": 307.739,
              "completed_http_requests": 36,
              "http_errors": [],
              "generated_tokens": 6705,
              "new_prefill_tokens": 26972,
              "timed_generated_tokens": 6669,
              "request_prefill_seconds_sum": 91.90304900000001,
              "request_decode_seconds_sum": 159.30165700000003,
              "pp_new_tokens_per_s": 293.48319009524914,
              "tg_pooled_per_request_tokens_per_s": 41.86397132077539,
              "generation_tokens_per_wall_second": 21.78794367954663,
              "cache_hit_tokens": 106425,
              "definitions": "Parsed retained SSE/JSON terminal usage and native timings. PP=prompt_n/prompt_seconds; TG=sum(predicted_n-1)/decode_seconds. Actual round wall includes tools and verifier work. No generation repeated."
            },
            "reviewed_outcome_count": 6
          },
          {
            "round": "hermes-2",
            "wall_seconds": 300.382,
            "outcome_count": 5,
            "generated_tokens": 7380,
            "api_calls": 35,
            "native_performance": {
              "wall_seconds": 300.382,
              "completed_http_requests": 35,
              "http_errors": [],
              "generated_tokens": 7380,
              "new_prefill_tokens": 19237,
              "timed_generated_tokens": 7345,
              "request_prefill_seconds_sum": 68.03446299999999,
              "request_decode_seconds_sum": 175.788464,
              "pp_new_tokens_per_s": 282.7537567247353,
              "tg_pooled_per_request_tokens_per_s": 41.78317412227915,
              "generation_tokens_per_wall_second": 24.568715835169883,
              "cache_hit_tokens": 119772,
              "definitions": "Parsed retained SSE/JSON terminal usage and native timings. PP=prompt_n/prompt_seconds; TG=sum(predicted_n-1)/decode_seconds. Actual round wall includes tools and verifier work. No generation repeated."
            },
            "reviewed_outcome_count": 6
          }
        ]
      },
      "health": [
        {
          "label": "health-C1",
          "wall_seconds": 40.445588815025985,
          "generated_tokens": 1649,
          "total": 10,
          "base_pass": 10,
          "plus_pass": 10
        },
        {
          "label": "long-health-C1",
          "wall_seconds": 48.2424732230138,
          "generated_tokens": 1335,
          "total": 8,
          "base_pass": 8,
          "plus_pass": 8
        }
      ]
    }
  ],
  "source_hashes": {
    "strix-v3-20260908/comparison.json": "147619c25d1abd861c3689a71c384d789fdcd23ae43755615192cf5f6f94e4df",
    "strix-v3-20260908/hard-panel/comparison.json": "37c27d24704a162788030b2fa4528e7321492934d1b5fa511f4dff4d8ac0471a"
  },
  "verification": {
    "status": "PASS",
    "official_speed_rows": 81,
    "official_quality_rows": 24,
    "archive_files": 2972,
    "report_sha256": "9b696fd62b38929f7664366abc8104eebd14d9618e952f65cffc2ef952394ca0",
    "native_scores_unchanged": true,
    "reviewed_memory_wording_artifacts_apply_to_previous_and_halo": true
  },
  "historical_evalscope": {
    "date": "2026-08-29",
    "profile": "qwen38-flash-next-h96-mtp-n1-uncapped",
    "classification": "historical, not rerun on v3",
    "quality_span_seconds": 11869.696209669113,
    "including_perf_span_seconds": 12046.300354480743,
    "stages": [
      {
        "stage": "arc",
        "start_epoch": 1787963313.8788962,
        "end_epoch": 1787964795.6449215,
        "seconds": 1481.7660253047943,
        "tasks": 1172
      },
      {
        "stage": "gpqa_diamond",
        "start_epoch": 1787964795.763053,
        "end_epoch": 1787970396.8102598,
        "seconds": 5601.047206878662,
        "tasks": 50
      },
      {
        "stage": "mmlu_pro",
        "start_epoch": 1787970396.8787158,
        "end_epoch": 1787972593.5807705,
        "seconds": 2196.7020547389984,
        "tasks": 70
      },
      {
        "stage": "gsm8k",
        "start_epoch": 1787972593.6486495,
        "end_epoch": 1787973813.100671,
        "seconds": 1219.452021598816,
        "tasks": 100
      },
      {
        "stage": "ifeval",
        "start_epoch": 1787973813.1662111,
        "end_epoch": 1787975183.575106,
        "seconds": 1370.408894777298,
        "tasks": 100
      },
      {
        "stage": "perf-1024x1024",
        "start_epoch": 1787975183.63826,
        "end_epoch": 1787975360.1792507,
        "seconds": 176.54099082946777
      }
    ],
    "scores": {
      "arc": [
        1143,
        1172
      ],
      "gpqa_diamond": [
        46,
        50
      ],
      "mmlu_pro": [
        61,
        70
      ],
      "gsm8k": [
        97,
        100
      ],
      "ifeval": [
        92,
        100
      ]
    }
  }
}
