[
  {
    "build_commit": "4b1a27fa0",
    "build_number": 11191,
    "cpu_info": "AMD Ryzen 3 4300U with Radeon Graphics         ",
    "gpu_info": "AMD Radeon(TM) Graphics",
    "backends": "Vulkan",
    "model_filename": "C:\\AIpcs-bench\\models\\llama-2-7b.Q4_0.gguf",
    "model_type": "llama 7B Q4_0",
    "model_size": 3825065984,
    "model_n_params": 6738415616,
    "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": 99,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "Vulkan0",
    "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": "2026-09-26T17:24:08Z",
    "avg_ns": 13172714020,
    "stddev_ns": 4047493,
    "avg_ts": 38.868227,
    "stddev_ts": 0.011941,
    "samples_ns": [ 13173151300, 13171515700, 13179119100, 13171756000, 13168028000 ],
    "samples_ts": [ 38.8669, 38.8718, 38.8493, 38.8711, 38.8821 ]
  },
  {
    "build_commit": "4b1a27fa0",
    "build_number": 11191,
    "cpu_info": "AMD Ryzen 3 4300U with Radeon Graphics         ",
    "gpu_info": "AMD Radeon(TM) Graphics",
    "backends": "Vulkan",
    "model_filename": "C:\\AIpcs-bench\\models\\llama-2-7b.Q4_0.gguf",
    "model_type": "llama 7B Q4_0",
    "model_size": 3825065984,
    "model_n_params": 6738415616,
    "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": 99,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "Vulkan0",
    "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": "2026-09-26T17:25:29Z",
    "avg_ns": 26531737820,
    "stddev_ns": 14504046,
    "avg_ts": 4.824412,
    "stddev_ts": 0.002638,
    "samples_ns": [ 26532315600, 26551337800, 26510636300, 26534574100, 26529825300 ],
    "samples_ts": [ 4.82431, 4.82085, 4.82825, 4.8239, 4.82476 ]
  },
  {
    "build_commit": "4b1a27fa0",
    "build_number": 11191,
    "cpu_info": "AMD Ryzen 3 4300U with Radeon Graphics         ",
    "gpu_info": "AMD Radeon(TM) Graphics",
    "backends": "Vulkan",
    "model_filename": "C:\\AIpcs-bench\\models\\llama-2-7b.Q4_0.gguf",
    "model_type": "llama 7B Q4_0",
    "model_size": 3825065984,
    "model_n_params": 6738415616,
    "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": 99,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "Vulkan0",
    "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": "2026-09-26T17:27:43Z",
    "avg_ns": 29730704560,
    "stddev_ns": 23808966,
    "avg_ts": 17.221262,
    "stddev_ts": 0.013795,
    "samples_ns": [ 29713206000, 29698923400, 29756656800, 29740691800, 29744044800 ],
    "samples_ts": [ 17.2314, 17.2397, 17.2062, 17.2155, 17.2135 ]
  },
  {
    "build_commit": "4b1a27fa0",
    "build_number": 11191,
    "cpu_info": "AMD Ryzen 3 4300U with Radeon Graphics         ",
    "gpu_info": "AMD Radeon(TM) Graphics",
    "backends": "Vulkan",
    "model_filename": "C:\\AIpcs-bench\\models\\llama-2-7b.Q4_0.gguf",
    "model_type": "llama 7B Q4_0",
    "model_size": 3825065984,
    "model_n_params": 6738415616,
    "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": 99,
    "n_cpu_moe": 0,
    "split_mode": "layer",
    "main_gpu": 0,
    "no_kv_offload": false,
    "flash_attn": -1,
    "devices": "Vulkan0",
    "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": "2026-09-26T17:33:21Z",
    "avg_ns": 45821856800,
    "stddev_ns": 142554588,
    "avg_ts": 2.793448,
    "stddev_ts": 0.008656,
    "samples_ns": [ 45775001300, 46074303700, 45777668900, 45727294100, 45755016000 ],
    "samples_ts": [ 2.79629, 2.77812, 2.79612, 2.7992, 2.79751 ]
  }
]