[
  {
    "build_commit": "e71b80510",
    "build_number": 10849,
    "cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
    "gpu_info": "",
    "backends": "CPU",
    "model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B.gguf",
    "model_type": "spark2_5 1.7B BF16",
    "model_size": 3415547904,
    "model_n_params": 1707657216,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 16,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": -1,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "auto",
    "tensor_split": "0.00",
    "tensor_buft_overrides": "none",
    "load_mode": "auto",
    "lazy_mode": "auto",
    "embeddings": false,
    "no_op_offload": 0,
    "no_host": false,
    "fit_target": 0,
    "fit_min_ctx": 0,
    "n_prompt": 512,
    "n_gen": 0,
    "n_depth": 0,
    "test_time": "2026-09-11T06:32:06Z",
    "avg_ns": 1498583726,
    "stddev_ns": 7171856,
    "avg_ts": 341.662152,
    "stddev_ts": 1.628172,
    "samples_ns": [ 1493166066, 1510351399, 1500283975, 1493415633, 1495701559 ],
    "samples_ts": [ 342.896, 338.994, 341.269, 342.838, 342.314 ]
  },
  {
    "build_commit": "e71b80510",
    "build_number": 10849,
    "cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
    "gpu_info": "",
    "backends": "CPU",
    "model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B.gguf",
    "model_type": "spark2_5 1.7B BF16",
    "model_size": 3415547904,
    "model_n_params": 1707657216,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 16,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": -1,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "auto",
    "tensor_split": "0.00",
    "tensor_buft_overrides": "none",
    "load_mode": "auto",
    "lazy_mode": "auto",
    "embeddings": false,
    "no_op_offload": 0,
    "no_host": false,
    "fit_target": 0,
    "fit_min_ctx": 0,
    "n_prompt": 0,
    "n_gen": 128,
    "n_depth": 0,
    "test_time": "2026-09-11T06:32:18Z",
    "avg_ns": 5062657211,
    "stddev_ns": 186447127,
    "avg_ts": 25.309483,
    "stddev_ts": 0.893384,
    "samples_ns": [ 4950579569, 4934896396, 5035243526, 5388250087, 5004316480 ],
    "samples_ts": [ 25.8556, 25.9377, 25.4208, 23.7554, 25.5779 ]
  },
  {
    "build_commit": "e71b80510",
    "build_number": 10849,
    "cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
    "gpu_info": "",
    "backends": "CPU",
    "model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q8_0.gguf",
    "model_type": "spark2_5 1.7B Q8_0",
    "model_size": 1814728704,
    "model_n_params": 1707657216,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 16,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": -1,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "auto",
    "tensor_split": "0.00",
    "tensor_buft_overrides": "none",
    "load_mode": "auto",
    "lazy_mode": "auto",
    "embeddings": false,
    "no_op_offload": 0,
    "no_host": false,
    "fit_target": 0,
    "fit_min_ctx": 0,
    "n_prompt": 512,
    "n_gen": 0,
    "n_depth": 0,
    "test_time": "2026-09-11T06:32:43Z",
    "avg_ns": 560100709,
    "stddev_ns": 15689530,
    "avg_ts": 914.690155,
    "stddev_ts": 25.391149,
    "samples_ns": [ 566521408, 541347341, 583132866, 553334911, 556167020 ],
    "samples_ts": [ 903.761, 945.788, 878.016, 925.299, 920.587 ]
  },
  {
    "build_commit": "e71b80510",
    "build_number": 10849,
    "cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
    "gpu_info": "",
    "backends": "CPU",
    "model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q8_0.gguf",
    "model_type": "spark2_5 1.7B Q8_0",
    "model_size": 1814728704,
    "model_n_params": 1707657216,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 16,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": -1,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "auto",
    "tensor_split": "0.00",
    "tensor_buft_overrides": "none",
    "load_mode": "auto",
    "lazy_mode": "auto",
    "embeddings": false,
    "no_op_offload": 0,
    "no_host": false,
    "fit_target": 0,
    "fit_min_ctx": 0,
    "n_prompt": 0,
    "n_gen": 128,
    "n_depth": 0,
    "test_time": "2026-09-11T06:32:47Z",
    "avg_ns": 1933840318,
    "stddev_ns": 51036422,
    "avg_ts": 66.225568,
    "stddev_ts": 1.706730,
    "samples_ns": [ 1896818220, 1923412956, 1937369806, 1892702916, 2018897692 ],
    "samples_ts": [ 67.4814, 66.5484, 66.069, 67.6282, 63.4009 ]
  },
  {
    "build_commit": "e71b80510",
    "build_number": 10849,
    "cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
    "gpu_info": "",
    "backends": "CPU",
    "model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q4_K_M.gguf",
    "model_type": "spark2_5 1.7B Q4_K - Medium",
    "model_size": 1102073856,
    "model_n_params": 1707657216,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 16,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": -1,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "auto",
    "tensor_split": "0.00",
    "tensor_buft_overrides": "none",
    "load_mode": "auto",
    "lazy_mode": "auto",
    "embeddings": false,
    "no_op_offload": 0,
    "no_host": false,
    "fit_target": 0,
    "fit_min_ctx": 0,
    "n_prompt": 512,
    "n_gen": 0,
    "n_depth": 0,
    "test_time": "2026-09-11T06:32:57Z",
    "avg_ns": 635046952,
    "stddev_ns": 3342779,
    "avg_ts": 806.257449,
    "stddev_ts": 4.239145,
    "samples_ns": [ 634661823, 637237702, 639487443, 631413242, 632434552 ],
    "samples_ts": [ 806.729, 803.468, 800.641, 810.879, 809.57 ]
  },
  {
    "build_commit": "e71b80510",
    "build_number": 10849,
    "cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
    "gpu_info": "",
    "backends": "CPU",
    "model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q4_K_M.gguf",
    "model_type": "spark2_5 1.7B Q4_K - Medium",
    "model_size": 1102073856,
    "model_n_params": 1707657216,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 16,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": -1,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "auto",
    "tensor_split": "0.00",
    "tensor_buft_overrides": "none",
    "load_mode": "auto",
    "lazy_mode": "auto",
    "embeddings": false,
    "no_op_offload": 0,
    "no_host": false,
    "fit_target": 0,
    "fit_min_ctx": 0,
    "n_prompt": 0,
    "n_gen": 128,
    "n_depth": 0,
    "test_time": "2026-09-11T06:33:01Z",
    "avg_ns": 1790378809,
    "stddev_ns": 14069215,
    "avg_ts": 71.496788,
    "stddev_ts": 0.562779,
    "samples_ns": [ 1803158642, 1794510633, 1803271959, 1776172087, 1774780727 ],
    "samples_ts": [ 70.9865, 71.3286, 70.9821, 72.0651, 72.1216 ]
  }
]