{
  "manifest": {
    "source": "moonshotai/Kimi-K3",
    "output": "Kimi-K3-Cubic-2.5Bit",
    "moe_schedule": "1-3:3@256,4-32:3@512,33-91:2@512,92:4@512",
    "linear_schedule": "",
    "conversion_hardware": {
      "device_type": "cuda",
      "device_count": 8
    },
    "shard_size_gib": 3.0,
    "a8_carrier_aware": true,
    "a8_correction_default": "enabled",
    "fitting_objective": "groupwise-least-squares",
    "reported_loss": "NRMSE = sqrt(joint SSE / source weight SSE)",
    "row_chunk_size": -1,
    "source_shards": 96,
    "expert_payload_bits": 2.369565217391304,
    "expert_effective_bits": 2.498641304347826,
    "converted_tensor_effective_bits": 2.498641304347826,
    "worker_scheduling": "dynamic_source_shard_queue",
    "output_partitioning": "deterministic_source_shard_index",
    "script": "quantize_k3.py",
    "script_sha256": "89fe8836bb407a027a2663637bc0380bd1adb29ffb2778f0879e606dc8ed31f3",
    "source_config_sha256": "9710e121a58d03ac92c8d6da287a19541994319afbbe6d6202af001ffd379213",
    "source_index_sha256": "a1c5210650ce71d2d3ae9ec5a101ac4afd3cf4b10091be589853437eb967febd",
    "output_shards": 341,
    "output_total_bytes": 964943224704,
    "combined_report": "cubic_quantization_report.json"
  },
  "loss_statistics": {
    "objective": "mean(continuous MSE, rounded-A8-carrier MSE)",
    "normalization": "loss is sqrt(joint SSE / source weight SSE), i.e. NRMSE; the fitting objective itself remains least squares.",
    "metadata_precision": "FP32 scale and FP16 a/b before recomputation",
    "by_bit": {
      "2": {
        "bits": 2,
        "loss": 0.4512510057287302,
        "clipped_percent": 12.230740958337455,
        "a8_correction_loss": 0.4512510057287302
      },
      "3": {
        "bits": 3,
        "loss": 0.18088323398973324,
        "clipped_percent": 2.966870055819044,
        "a8_correction_loss": 0.18091672638061443
      },
      "4": {
        "bits": 4,
        "loss": 0.0430471542191854,
        "clipped_percent": 0.5635432713156114,
        "a8_correction_loss": 0.04324462046872603
      }
    },
    "by_bit_and_group_size": {
      "2@512": {
        "bits": 2,
        "loss": 0.4512510057287302,
        "clipped_percent": 12.230740958337455,
        "a8_correction_loss": 0.4512510057287302,
        "group_size": 512
      },
      "3@256": {
        "bits": 3,
        "loss": 0.17960835023454785,
        "clipped_percent": 2.6970932295353056,
        "a8_correction_loss": 0.1795795260456478,
        "group_size": 256
      },
      "3@512": {
        "bits": 3,
        "loss": 0.18100745927884193,
        "clipped_percent": 2.994778003365638,
        "a8_correction_loss": 0.18104699922459405,
        "group_size": 512
      },
      "4@512": {
        "bits": 4,
        "loss": 0.0430471542191854,
        "clipped_percent": 0.5635432713156114,
        "a8_correction_loss": 0.04324462046872603,
        "group_size": 512
      }
    }
  },
  "audit": {
    "checkpoint": "Kimi-K3-Cubic-2.5Bit",
    "shards": 341,
    "tensors": 991812,
    "total_size": 964943224704,
    "max_shard_bytes": 3221225472,
    "widths_present": [
      2,
      3,
      4
    ],
    "converted_tensor_effective_bits": 2.498641304347826,
    "dtype_counts": {
      "BF16": 2122,
      "F32": 247802,
      "F16": 494592,
      "U8": 247296
    }
  }
}