[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-all-minilm-l6-v2-1":3},{"id":4,"slug":5,"name":6,"hf_id":6,"organization":7,"architecture":8,"architecture_config":9,"parameters":13,"parameters_label":14,"context_length":15,"license":16,"downloads":17,"likes":18,"status":19,"description":16,"huggingface_url":20,"created_at":21,"seo":22,"category":25,"family":28,"score":30,"variants":31,"quantizations":32,"requirements":59,"gpu_recommendations":113,"fitting_gpus":175,"community":210},547,"all-minilm-l6-v2-1","Xenova\u002Fall-MiniLM-L6-v2","Xenova","bert",{"layers":10,"head_dim":11,"hidden_size":12},6,32,384,22337280,"22.3M",512,null,4128194,153,"published","https:\u002F\u002Fhuggingface.co\u002FXenova\u002Fall-MiniLM-L6-v2","2026-10-12T06:12:41+00:00",{"title":6,"description":23,"image":16,"robots":24,"canonical_url":16},"AI model deployment & compute intelligence — compare AI models, GPU requirements, benchmarks, cloud GPU rental pricing and deployment cost analysis for DeepSeek, Qwen, Llama, Wan and more.","index, follow",{"name":26,"slug":27},"Embedding \u002F RAG","embedding",{"name":7,"slug":29},"xenova",0.0102,[],[33,38,43,48,52,56],{"format":34,"bits":35,"size_factor":36,"quality_loss":37},"AWQ",4,0.263,0.03,{"format":39,"bits":40,"size_factor":41,"quality_loss":42},"FP16",16,1,0,{"format":44,"bits":45,"size_factor":46,"quality_loss":47},"FP8",8,0.5,0.01,{"format":49,"bits":35,"size_factor":50,"quality_loss":51},"GGUF",0.25,0.05,{"format":53,"bits":35,"size_factor":54,"quality_loss":55},"GPTQ",0.275,0.04,{"format":57,"bits":45,"size_factor":46,"quality_loss":58},"INT8",0.02,{"FP16":60,"FP8":81,"INT8":91,"AWQ":95,"GPTQ":105,"GGUF":109},{"minimum":61,"production":68,"recommended":74},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":55,"kv_cache_gb":58,"vram_gb":64,"ram_gb":11,"disk_gb":65,"requirement_source":66,"confidence":67},"minimum",4096,2.32,39.06,"inferred",0.95,{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":55,"kv_cache_gb":71,"vram_gb":72,"ram_gb":11,"disk_gb":73,"requirement_source":66,"confidence":67},"production",16384,3,6.73,104.06,{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":55,"kv_cache_gb":78,"vram_gb":79,"ram_gb":11,"disk_gb":80,"requirement_source":66,"confidence":67},"recommended",8192,2,0.38,2.95,65.06,{"minimum":82,"production":85,"recommended":88},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":58,"kv_cache_gb":58,"vram_gb":83,"ram_gb":11,"disk_gb":84,"requirement_source":66,"confidence":67},2.29,39.03,{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":58,"kv_cache_gb":71,"vram_gb":86,"ram_gb":11,"disk_gb":87,"requirement_source":66,"confidence":67},6.7,104.03,{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":58,"kv_cache_gb":78,"vram_gb":89,"ram_gb":11,"disk_gb":90,"requirement_source":66,"confidence":67},2.92,65.03,{"minimum":92,"production":93,"recommended":94},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":58,"kv_cache_gb":58,"vram_gb":83,"ram_gb":11,"disk_gb":84,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":58,"kv_cache_gb":71,"vram_gb":86,"ram_gb":11,"disk_gb":87,"requirement_source":66,"confidence":67},{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":58,"kv_cache_gb":78,"vram_gb":89,"ram_gb":11,"disk_gb":90,"requirement_source":66,"confidence":67},{"minimum":96,"production":99,"recommended":102},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":47,"kv_cache_gb":58,"vram_gb":97,"ram_gb":11,"disk_gb":98,"requirement_source":66,"confidence":67},2.28,39.02,{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":47,"kv_cache_gb":71,"vram_gb":100,"ram_gb":11,"disk_gb":101,"requirement_source":66,"confidence":67},6.69,104.02,{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":47,"kv_cache_gb":78,"vram_gb":103,"ram_gb":11,"disk_gb":104,"requirement_source":66,"confidence":67},2.91,65.02,{"minimum":106,"production":107,"recommended":108},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":47,"kv_cache_gb":58,"vram_gb":97,"ram_gb":11,"disk_gb":98,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":47,"kv_cache_gb":71,"vram_gb":100,"ram_gb":11,"disk_gb":101,"requirement_source":66,"confidence":67},{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":47,"kv_cache_gb":78,"vram_gb":103,"ram_gb":11,"disk_gb":104,"requirement_source":66,"confidence":67},{"minimum":110,"production":111,"recommended":112},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":47,"kv_cache_gb":58,"vram_gb":97,"ram_gb":11,"disk_gb":98,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":47,"kv_cache_gb":71,"vram_gb":100,"ram_gb":11,"disk_gb":101,"requirement_source":66,"confidence":67},{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":47,"kv_cache_gb":78,"vram_gb":103,"ram_gb":11,"disk_gb":104,"requirement_source":66,"confidence":67},{"recommended":114,"cheapest":133,"performance":142,"min_complexity":159,"cluster_options":172,"no_match":173,"required_vram_gb":103,"candidate_count":11,"usage":174},{"gpu_model":115,"gpu_model_id":116,"gpu_count":41,"total_vram_gb":117,"hour_price":118,"monthly_cost":119,"providers":120,"bandwidth_gbps":122,"fp16_tflops":123,"interconnect_score":124,"parallel_efficiency":41,"score":125,"tier":126,"perf_metric":127,"perf_label":128,"perf_value":129,"workload":16,"cost_metric":130},"RTX 3080 Ti",36,12,0.108,78.84,[121],"vast",912,68,40,0.5595,"cheapest","tok\u002Fs","91200 tok\u002Fs",91200,{"effective_value":131,"effective_unit":127,"capacity_factor":132},63840,0.7,{"gpu_model":134,"gpu_model_id":135,"gpu_count":41,"total_vram_gb":40,"hour_price":136,"monthly_cost":137,"providers":138,"bandwidth_gbps":42,"fp16_tflops":42,"interconnect_score":124,"parallel_efficiency":41,"score":139,"tier":126,"perf_metric":127,"perf_label":140,"perf_value":42,"workload":16,"cost_metric":141},"Tesla V100",17,0.0489,35.7,[121],0.5378,"0 tok\u002Fs",{"effective_value":42,"effective_unit":127,"capacity_factor":132},{"gpu_model":143,"gpu_model_id":144,"gpu_count":45,"total_vram_gb":145,"hour_price":146,"monthly_cost":147,"providers":148,"bandwidth_gbps":150,"fp16_tflops":151,"interconnect_score":124,"parallel_efficiency":152,"score":153,"tier":154,"perf_metric":127,"perf_label":155,"perf_value":156,"workload":16,"cost_metric":157},"H200 SXM",11,1128,3.5,20440,[149],"lambda",4800,989,0.4,0.2197,"balanced","1536000 tok\u002Fs",1536000,{"effective_value":158,"effective_unit":127,"capacity_factor":132},1075200,{"gpu_model":160,"gpu_model_id":161,"gpu_count":41,"total_vram_gb":45,"hour_price":162,"monthly_cost":163,"providers":164,"bandwidth_gbps":165,"fp16_tflops":166,"interconnect_score":124,"parallel_efficiency":41,"score":167,"tier":126,"perf_metric":127,"perf_label":168,"perf_value":169,"workload":16,"cost_metric":170},"RTX 4060 Ti",29,0.0811,59.2,[121],288,45,0.5878,"28800 tok\u002Fs",28800,{"effective_value":171,"effective_unit":127,"capacity_factor":132},20160,[],false,"value",[176,180,184,193,202],{"name":134,"vram_gb":40,"cheapest_hour":136,"cost":177,"provider":121,"estimated_tps":42},{"hourly":136,"daily":178,"monthly":137,"yearly":179},1.17,428.36,{"name":160,"vram_gb":45,"cheapest_hour":162,"cost":181,"provider":121,"estimated_tps":169},{"hourly":162,"daily":182,"monthly":163,"yearly":183},1.95,710.44,{"name":185,"vram_gb":186,"cheapest_hour":187,"cost":188,"provider":121,"estimated_tps":192},"RTX 3080",10,0.0874,{"hourly":187,"daily":189,"monthly":190,"yearly":191},2.1,63.8,765.62,76000,{"name":194,"vram_gb":195,"cheapest_hour":196,"cost":197,"provider":121,"estimated_tps":201},"L4",24,0.1044,{"hourly":196,"daily":198,"monthly":199,"yearly":200},2.51,76.21,914.54,30000,{"name":203,"vram_gb":45,"cheapest_hour":204,"cost":205,"provider":121,"estimated_tps":209},"RTX 5060 Ti",0.1072,{"hourly":204,"daily":206,"monthly":207,"yearly":208},2.57,78.26,939.07,44800,{"posts_count":42,"benchmarks_count":42}]