[
  {
    "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": 8,
    "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": "2026-09-11T17:16:53Z",
    "avg_ns": 1253292754,
    "stddev_ns": 79129486,
    "avg_ts": 409.796891,
    "stddev_ts": 25.209212,
    "samples_ns": [ 1190927743, 1190669420, 1208414068, 1318310015, 1358142528 ],
    "samples_ts": [ 429.917, 430.01, 423.696, 388.376, 376.985 ]
  },
  {
    "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": 8,
    "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": "2026-09-11T17:17:01Z",
    "avg_ns": 2909185423,
    "stddev_ns": 35614966,
    "avg_ts": 44.003861,
    "stddev_ts": 0.540189,
    "samples_ns": [ 2935902159, 2946667991, 2878606593, 2919344964, 2865405409 ],
    "samples_ts": [ 43.5982, 43.4389, 44.466, 43.8455, 44.6708 ]
  }
]