[
  {
    "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\\gemma-4-E4B-it-Q4_0.gguf",
    "model_type": "gemma4 E4B Q4_0",
    "model_size": 4574983336,
    "model_n_params": 7463013674,
    "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": "2026-09-25T22:50:42Z",
    "avg_ns": 173075240,
    "stddev_ns": 9008122,
    "avg_ts": 2964.325454,
    "stddev_ts": 145.939554,
    "samples_ns": [ 188604700, 169744300, 172900600, 167128400, 166998200 ],
    "samples_ts": [ 2714.67, 3016.3, 2961.24, 3063.51, 3065.9 ]
  },
  {
    "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\\gemma-4-E4B-it-Q4_0.gguf",
    "model_type": "gemma4 E4B Q4_0",
    "model_size": 4574983336,
    "model_n_params": 7463013674,
    "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": "2026-09-25T22:50:43Z",
    "avg_ns": 1891703960,
    "stddev_ns": 7948069,
    "avg_ts": 67.664816,
    "stddev_ts": 0.283076,
    "samples_ns": [ 1887363600, 1905175000, 1888329100, 1892320700, 1885331400 ],
    "samples_ts": [ 67.8195, 67.1854, 67.7848, 67.6418, 67.8926 ]
  },
  {
    "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\\gemma-4-E4B-it-Q4_0.gguf",
    "model_type": "gemma4 E4B Q4_0",
    "model_size": 4574983336,
    "model_n_params": 7463013674,
    "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": "2026-09-25T22:50:52Z",
    "avg_ns": 188146400,
    "stddev_ns": 4106055,
    "avg_ts": 2722.313054,
    "stddev_ts": 58.881984,
    "samples_ns": [ 190759700, 193948300, 186464300, 185631500, 183928200 ],
    "samples_ts": [ 2684.01, 2639.88, 2745.83, 2758.15, 2783.69 ]
  },
  {
    "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\\gemma-4-E4B-it-Q4_0.gguf",
    "model_type": "gemma4 E4B Q4_0",
    "model_size": 4574983336,
    "model_n_params": 7463013674,
    "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": "2026-09-25T22:50:55Z",
    "avg_ns": 1967442540,
    "stddev_ns": 9278088,
    "avg_ts": 65.060237,
    "stddev_ts": 0.306929,
    "samples_ns": [ 1965270600, 1963170100, 1976067000, 1977411500, 1955293500 ],
    "samples_ts": [ 65.131, 65.2007, 64.7751, 64.7311, 65.4633 ]
  }
]