GGUF
conversational
File size: 12,538 Bytes
c34481e
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
{"cfg":"default","round":1,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 96, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": true, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T03:03:26Z", "avg_ns": 2765225085, "stddev_ns": 98412067, "avg_ts": 185.274050, "stddev_ts": 6.593748, "samples_ns": [ 2834812906, 2695637265 ],"samples_ts": [ 180.612, 189.937 ]}
{"cfg":"default","round":1,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 96, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": true, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 64, "n_depth": 0, "test_time": "2026-10-27T03:03:34Z", "avg_ns": 11223753320, "stddev_ns": 156571936, "avg_ts": 5.702747, "stddev_ts": 0.079554, "samples_ns": [ 11113040293, 11334466348 ],"samples_ts": [ 5.759, 5.64649 ]}
{"cfg":"readme","round":1,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T03:03:58Z", "avg_ns": 2270165341, "stddev_ns": 42364043, "avg_ts": 225.573510, "stddev_ts": 4.209470, "samples_ns": [ 2240209477, 2300121206 ],"samples_ts": [ 228.55, 222.597 ]}
{"cfg":"readme","round":1,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 64, "n_depth": 0, "test_time": "2026-10-27T03:04:05Z", "avg_ns": 3809386797, "stddev_ns": 143560921, "avg_ts": 16.812543, "stddev_ts": 0.633599, "samples_ns": [ 3910899680, 3707873915 ],"samples_ts": [ 16.3645, 17.2606 ]}
{"cfg":"default","round":2,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 96, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": true, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T03:04:13Z", "avg_ns": 2678488890, "stddev_ns": 59513110, "avg_ts": 191.199753, "stddev_ts": 4.248247, "samples_ns": [ 2720570983, 2636406798 ],"samples_ts": [ 188.196, 194.204 ]}
{"cfg":"default","round":2,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 96, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": true, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 64, "n_depth": 0, "test_time": "2026-10-27T03:04:21Z", "avg_ns": 11184174542, "stddev_ns": 171063328, "avg_ts": 5.723041, "stddev_ts": 0.087535, "samples_ns": [ 11305134536, 11063214549 ],"samples_ts": [ 5.66114, 5.78494 ]}
{"cfg":"readme","round":2,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T03:04:44Z", "avg_ns": 2230540798, "stddev_ns": 2074160, "avg_ts": 229.540846, "stddev_ts": 0.213337, "samples_ns": [ 2232006691, 2229074906 ],"samples_ts": [ 229.39, 229.692 ]}
{"cfg":"readme","round":2,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 64, "n_depth": 0, "test_time": "2026-10-27T03:04:51Z", "avg_ns": 3739550072, "stddev_ns": 42169174, "avg_ts": 17.115447, "stddev_ts": 0.193003, "samples_ns": [ 3769368181, 3709731963 ],"samples_ts": [ 16.979, 17.2519 ]}
{"cfg":"default","round":3,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 96, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": true, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T03:04:59Z", "avg_ns": 2688425234, "stddev_ns": 64459026, "avg_ts": 190.500819, "stddev_ts": 4.567543, "samples_ns": [ 2642845819, 2734004649 ],"samples_ts": [ 193.731, 187.271 ]}
{"cfg":"default","round":3,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 96, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": true, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 64, "n_depth": 0, "test_time": "2026-10-27T03:05:07Z", "avg_ns": 11390615765, "stddev_ns": 300004688, "avg_ts": 5.620610, "stddev_ts": 0.148035, "samples_ns": [ 11602751088, 11178480443 ],"samples_ts": [ 5.51593, 5.72529 ]}
{"cfg":"readme","round":3,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T03:05:31Z", "avg_ns": 2191842703, "stddev_ns": 63027699, "avg_ts": 233.690022, "stddev_ts": 6.719891, "samples_ns": [ 2147275389, 2236410017 ],"samples_ts": [ 238.442, 228.938 ]}
{"cfg":"readme","round":3,"build_commit": "1268edac5", "build_number": 11707, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": 0, "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, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 64, "n_depth": 0, "test_time": "2026-10-27T03:05:38Z", "avg_ns": 3696916664, "stddev_ns": 62609087, "avg_ts": 17.314207, "stddev_ts": 0.293224, "samples_ns": [ 3741187933, 3652645396 ],"samples_ts": [ 17.1069, 17.5215 ]}