[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-bge-large-zh-v15":3},{"id":4,"slug":5,"name":6,"hf_id":7,"organization":8,"architecture":9,"architecture_config":10,"parameters":11,"parameters_label":12,"context_length":13,"license":14,"downloads":15,"likes":16,"status":17,"description":18,"huggingface_url":19,"created_at":20,"seo":21,"category":23,"family":26,"score":28,"variants":29,"quantizations":30,"requirements":57,"gpu_recommendations":113,"fitting_gpus":156,"community":189},45,"bge-large-zh-v15","BGE-large-zh-v1.5","BAAI\u002Fbge-large-zh-v1.5","BAAI","bge",null,326000000,"326M",512,"MIT",690000,1200,"published","BGE 中文向量模型，1024 维。","https:\u002F\u002Fhuggingface.co\u002FBAAI\u002Fbge-large-zh-v1.5","2026-08-12T02:22:25+00:00",{"title":6,"description":18,"image":10,"robots":22,"canonical_url":10},"index, follow",{"name":24,"slug":25},"Embedding \u002F RAG","embedding",{"name":27,"slug":9},"BGE",0.0794,[],[31,36,41,46,50,54],{"format":32,"bits":33,"size_factor":34,"quality_loss":35},"AWQ",4,0.263,0.03,{"format":37,"bits":38,"size_factor":39,"quality_loss":40},"FP16",16,1,0,{"format":42,"bits":43,"size_factor":44,"quality_loss":45},"FP8",8,0.5,0.01,{"format":47,"bits":33,"size_factor":48,"quality_loss":49},"GGUF",0.25,0.05,{"format":51,"bits":33,"size_factor":52,"quality_loss":53},"GPTQ",0.275,0.04,{"format":55,"bits":43,"size_factor":44,"quality_loss":56},"INT8",0.02,{"FP16":58,"FP8":79,"INT8":90,"AWQ":94,"GPTQ":105,"GGUF":109},{"minimum":59,"production":68,"recommended":73},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":62,"kv_cache_gb":40,"vram_gb":63,"ram_gb":64,"disk_gb":65,"requirement_source":66,"confidence":67},"minimum",4096,0.61,2.08,32,39.95,"estimated",0.95,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":62,"kv_cache_gb":40,"vram_gb":71,"ram_gb":64,"disk_gb":72,"requirement_source":66,"confidence":67},"production",16384,2.63,104.95,{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":62,"kv_cache_gb":40,"vram_gb":77,"ram_gb":64,"disk_gb":78,"requirement_source":66,"confidence":67},"recommended",8192,2,2.29,65.95,{"minimum":80,"production":84,"recommended":87},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":81,"kv_cache_gb":40,"vram_gb":82,"ram_gb":64,"disk_gb":83,"requirement_source":66,"confidence":67},0.3,1.64,39.47,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":81,"kv_cache_gb":40,"vram_gb":85,"ram_gb":64,"disk_gb":86,"requirement_source":66,"confidence":67},2.15,104.47,{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":81,"kv_cache_gb":40,"vram_gb":88,"ram_gb":64,"disk_gb":89,"requirement_source":66,"confidence":67},1.83,65.47,{"minimum":91,"production":92,"recommended":93},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":81,"kv_cache_gb":40,"vram_gb":82,"ram_gb":64,"disk_gb":83,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":81,"kv_cache_gb":40,"vram_gb":85,"ram_gb":64,"disk_gb":86,"requirement_source":66,"confidence":67},{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":81,"kv_cache_gb":40,"vram_gb":88,"ram_gb":64,"disk_gb":89,"requirement_source":66,"confidence":67},{"minimum":95,"production":99,"recommended":102},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":96,"kv_cache_gb":40,"vram_gb":97,"ram_gb":64,"disk_gb":98,"requirement_source":66,"confidence":67},0.16,1.44,39.25,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":96,"kv_cache_gb":40,"vram_gb":100,"ram_gb":64,"disk_gb":101,"requirement_source":66,"confidence":67},1.93,104.25,{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":96,"kv_cache_gb":40,"vram_gb":103,"ram_gb":64,"disk_gb":104,"requirement_source":66,"confidence":67},1.62,65.25,{"minimum":106,"production":107,"recommended":108},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":96,"kv_cache_gb":40,"vram_gb":97,"ram_gb":64,"disk_gb":98,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":96,"kv_cache_gb":40,"vram_gb":100,"ram_gb":64,"disk_gb":101,"requirement_source":66,"confidence":67},{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":96,"kv_cache_gb":40,"vram_gb":103,"ram_gb":64,"disk_gb":104,"requirement_source":66,"confidence":67},{"minimum":110,"production":111,"recommended":112},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":96,"kv_cache_gb":40,"vram_gb":97,"ram_gb":64,"disk_gb":98,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":96,"kv_cache_gb":40,"vram_gb":100,"ram_gb":64,"disk_gb":101,"requirement_source":66,"confidence":67},{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":96,"kv_cache_gb":40,"vram_gb":103,"ram_gb":64,"disk_gb":104,"requirement_source":66,"confidence":67},{"recommended":114,"cheapest":131,"performance":134,"min_complexity":145,"cluster_options":153,"no_match":154,"required_vram_gb":103,"candidate_count":33,"usage":155},{"gpu_model":115,"gpu_model_id":116,"gpu_count":39,"total_vram_gb":43,"hour_price":117,"monthly_cost":118,"providers":119,"bandwidth_gbps":121,"fp16_tflops":116,"interconnect_score":122,"parallel_efficiency":39,"score":123,"tier":124,"perf_metric":125,"perf_label":126,"perf_value":127,"workload":10,"cost_metric":128},"RTX 5060 Ti",24,0.0544,39.71,[120],"vast",448,40,0.5464,"cheapest","vectors\u002Fs","5600 vec\u002Fs",5600,{"effective_value":129,"effective_unit":125,"capacity_factor":130},4480,0.8,{"gpu_model":115,"gpu_model_id":116,"gpu_count":39,"total_vram_gb":43,"hour_price":117,"monthly_cost":118,"providers":132,"bandwidth_gbps":121,"fp16_tflops":116,"interconnect_score":122,"parallel_efficiency":39,"score":123,"tier":124,"perf_metric":125,"perf_label":126,"perf_value":127,"workload":10,"cost_metric":133},[120],{"effective_value":129,"effective_unit":125,"capacity_factor":130},{"gpu_model":115,"gpu_model_id":116,"gpu_count":43,"total_vram_gb":135,"hour_price":117,"monthly_cost":136,"providers":137,"bandwidth_gbps":121,"fp16_tflops":116,"interconnect_score":122,"parallel_efficiency":138,"score":139,"tier":140,"perf_metric":125,"perf_label":141,"perf_value":142,"workload":10,"cost_metric":143},64,317.7,[120],0.4,0.3636,"balanced","44800 vec\u002Fs",44800,{"effective_value":144,"effective_unit":125,"capacity_factor":130},35840,{"gpu_model":115,"gpu_model_id":116,"gpu_count":76,"total_vram_gb":38,"hour_price":117,"monthly_cost":146,"providers":147,"bandwidth_gbps":121,"fp16_tflops":116,"interconnect_score":122,"parallel_efficiency":130,"score":148,"tier":124,"perf_metric":125,"perf_label":149,"perf_value":150,"workload":10,"cost_metric":151},79.42,[120],0.451,"11200 vec\u002Fs",11200,{"effective_value":152,"effective_unit":125,"capacity_factor":130},8960,[],false,"value",[157,166,173,178,186],{"name":158,"vram_gb":159,"cheapest_hour":160,"cost":161,"provider":120,"estimated_tps":165},"RTX 5070",12,0.0101,{"hourly":160,"daily":162,"monthly":163,"yearly":164},0.24,7.37,88.48,4200,{"name":167,"vram_gb":38,"cheapest_hour":168,"cost":169,"provider":120,"estimated_tps":40},"Tesla V100",0.0272,{"hourly":168,"daily":170,"monthly":171,"yearly":172},0.65,19.86,238.27,{"name":115,"vram_gb":43,"cheapest_hour":117,"cost":174,"provider":120,"estimated_tps":177},{"hourly":117,"daily":175,"monthly":118,"yearly":176},1.31,476.54,2800,{"name":179,"vram_gb":116,"cheapest_hour":180,"cost":181,"provider":120,"estimated_tps":185},"RTX 3090",0.0678,{"hourly":180,"daily":182,"monthly":183,"yearly":184},1.63,49.49,593.93,5850,{"name":187,"vram_gb":38,"cheapest_hour":180,"cost":188,"provider":120,"estimated_tps":40},"RTX 4070S Ti",{"hourly":180,"daily":182,"monthly":183,"yearly":184},{"posts_count":40,"benchmarks_count":40}]