[
  {
    "build_commit": "4b1a27fa0",
    "build_number": 11191,
    "cpu_info": "AMD Ryzen 9 7900X 12-Core Processor            ",
    "gpu_info": "NVIDIA GeForce RTX 4060",
    "backends": "CUDA",
    "model_filename": "D:\\AIpcs-bench\\models\\Qwen3.5-9B-Q4_K_M.gguf",
    "model_type": "qwen35 9B Q4_K - Medium",
    "model_size": 5669554176,
    "model_n_params": 8953803264,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 12,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": 99,
    "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": "2026-09-25T22:51:17Z",
    "avg_ns": 269966200,
    "stddev_ns": 5734349,
    "avg_ts": 1897.219921,
    "stddev_ts": 40.385780,
    "samples_ns": [ 276961100, 263170500, 272618300, 272098800, 264982300 ],
    "samples_ts": [ 1848.64, 1945.51, 1878.08, 1881.67, 1932.2 ]
  },
  {
    "build_commit": "4b1a27fa0",
    "build_number": 11191,
    "cpu_info": "AMD Ryzen 9 7900X 12-Core Processor            ",
    "gpu_info": "NVIDIA GeForce RTX 4060",
    "backends": "CUDA",
    "model_filename": "D:\\AIpcs-bench\\models\\Qwen3.5-9B-Q4_K_M.gguf",
    "model_type": "qwen35 9B Q4_K - Medium",
    "model_size": 5669554176,
    "model_n_params": 8953803264,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 12,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": 99,
    "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": "2026-09-25T22:51:19Z",
    "avg_ns": 2811566100,
    "stddev_ns": 4002430,
    "avg_ts": 45.526302,
    "stddev_ts": 0.064844,
    "samples_ns": [ 2815903800, 2809721300, 2814390200, 2805765300, 2812049900 ],
    "samples_ts": [ 45.4561, 45.5561, 45.4805, 45.6204, 45.5184 ]
  },
  {
    "build_commit": "4b1a27fa0",
    "build_number": 11191,
    "cpu_info": "AMD Ryzen 9 7900X 12-Core Processor            ",
    "gpu_info": "NVIDIA GeForce RTX 4060",
    "backends": "CUDA",
    "model_filename": "D:\\AIpcs-bench\\models\\Qwen3.5-9B-Q4_K_M.gguf",
    "model_type": "qwen35 9B Q4_K - Medium",
    "model_size": 5669554176,
    "model_n_params": 8953803264,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 12,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": 99,
    "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": 4096,
    "test_time": "2026-09-25T22:51:33Z",
    "avg_ns": 283210480,
    "stddev_ns": 2547225,
    "avg_ts": 1807.958948,
    "stddev_ts": 16.155841,
    "samples_ns": [ 287227600, 284145900, 282105400, 281685800, 280887700 ],
    "samples_ts": [ 1782.56, 1801.89, 1814.92, 1817.63, 1822.79 ]
  },
  {
    "build_commit": "4b1a27fa0",
    "build_number": 11191,
    "cpu_info": "AMD Ryzen 9 7900X 12-Core Processor            ",
    "gpu_info": "NVIDIA GeForce RTX 4060",
    "backends": "CUDA",
    "model_filename": "D:\\AIpcs-bench\\models\\Qwen3.5-9B-Q4_K_M.gguf",
    "model_type": "qwen35 9B Q4_K - Medium",
    "model_size": 5669554176,
    "model_n_params": 8953803264,
    "n_batch": 2048,
    "n_ubatch": 512,
    "n_threads": 12,
    "cpu_mask": "0x0",
    "cpu_strict": false,
    "poll": 50,
    "type_k": "f16",
    "type_v": "f16",
    "n_gpu_layers": 99,
    "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": 4096,
    "test_time": "2026-09-25T22:51:38Z",
    "avg_ns": 2869751720,
    "stddev_ns": 7967213,
    "avg_ts": 44.603436,
    "stddev_ts": 0.123656,
    "samples_ns": [ 2881487600, 2867519300, 2862673700, 2873931200, 2863146800 ],
    "samples_ts": [ 44.4215, 44.6379, 44.7134, 44.5383, 44.7061 ]
  }
]