[
  {
    "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": 4,
    "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": "2026-09-11T17:14:01Z",
    "avg_ns": 2437249430,
    "stddev_ns": 66433948,
    "avg_ts": 210.202021,
    "stddev_ts": 5.922750,
    "samples_ns": [ 2468232968, 2479407287, 2475612647, 2441614629, 2321379621 ],
    "samples_ts": [ 207.436, 206.501, 206.817, 209.697, 220.558 ]
  },
  {
    "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": 4,
    "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": "2026-09-11T17:14:15Z",
    "avg_ns": 5289126007,
    "stddev_ns": 63024171,
    "avg_ts": 24.203349,
    "stddev_ts": 0.288883,
    "samples_ns": [ 5363916055, 5306624609, 5325596808, 5238325957, 5211166606 ],
    "samples_ts": [ 23.8632, 24.1208, 24.0349, 24.4353, 24.5626 ]
  }
]