[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-all-minilm-l12-v2":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":116,"fitting_gpus":170,"community":205},528,"all-minilm-l12-v2","sentence-transformers\u002Fall-MiniLM-L12-v2","sentence-transformers","bert",{"layers":10,"head_dim":11,"hidden_size":12},12,32,384,32954112,"33M",512,null,4196036,330,"published","https:\u002F\u002Fhuggingface.co\u002Fsentence-transformers\u002Fall-MiniLM-L12-v2","2026-09-10T12:13:41+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":29,"slug":7},"Sentence-transformers",0.0375,[],[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":80,"INT8":90,"AWQ":94,"GPTQ":104,"GGUF":112},{"minimum":61,"production":69,"recommended":74},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":64,"kv_cache_gb":42,"vram_gb":65,"ram_gb":11,"disk_gb":66,"requirement_source":67,"confidence":68},"minimum",4096,0.06,1.3,39.1,"inferred",0.95,{"scenario":70,"context_length":71,"batch_size":35,"weight_gb":64,"kv_cache_gb":42,"vram_gb":72,"ram_gb":11,"disk_gb":73,"requirement_source":67,"confidence":68},"production",16384,1.78,104.1,{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":64,"kv_cache_gb":42,"vram_gb":78,"ram_gb":11,"disk_gb":79,"requirement_source":67,"confidence":68},"recommended",8192,2,1.47,65.1,{"minimum":81,"production":84,"recommended":87},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":37,"kv_cache_gb":42,"vram_gb":82,"ram_gb":11,"disk_gb":83,"requirement_source":67,"confidence":68},1.25,39.05,{"scenario":70,"context_length":71,"batch_size":35,"weight_gb":37,"kv_cache_gb":42,"vram_gb":85,"ram_gb":11,"disk_gb":86,"requirement_source":67,"confidence":68},1.73,104.05,{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":37,"kv_cache_gb":42,"vram_gb":88,"ram_gb":11,"disk_gb":89,"requirement_source":67,"confidence":68},1.43,65.05,{"minimum":91,"production":92,"recommended":93},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":37,"kv_cache_gb":42,"vram_gb":82,"ram_gb":11,"disk_gb":83,"requirement_source":67,"confidence":68},{"scenario":70,"context_length":71,"batch_size":35,"weight_gb":37,"kv_cache_gb":42,"vram_gb":85,"ram_gb":11,"disk_gb":86,"requirement_source":67,"confidence":68},{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":37,"kv_cache_gb":42,"vram_gb":88,"ram_gb":11,"disk_gb":89,"requirement_source":67,"confidence":68},{"minimum":95,"production":98,"recommended":101},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":58,"kv_cache_gb":42,"vram_gb":96,"ram_gb":11,"disk_gb":97,"requirement_source":67,"confidence":68},1.23,39.02,{"scenario":70,"context_length":71,"batch_size":35,"weight_gb":58,"kv_cache_gb":42,"vram_gb":99,"ram_gb":11,"disk_gb":100,"requirement_source":67,"confidence":68},1.7,104.02,{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":58,"kv_cache_gb":42,"vram_gb":102,"ram_gb":11,"disk_gb":103,"requirement_source":67,"confidence":68},1.4,65.02,{"minimum":105,"production":107,"recommended":110},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":58,"kv_cache_gb":42,"vram_gb":96,"ram_gb":11,"disk_gb":106,"requirement_source":67,"confidence":68},39.03,{"scenario":70,"context_length":71,"batch_size":35,"weight_gb":58,"kv_cache_gb":42,"vram_gb":108,"ram_gb":11,"disk_gb":109,"requirement_source":67,"confidence":68},1.71,104.03,{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":58,"kv_cache_gb":42,"vram_gb":102,"ram_gb":11,"disk_gb":111,"requirement_source":67,"confidence":68},65.03,{"minimum":113,"production":114,"recommended":115},{"scenario":62,"context_length":63,"batch_size":41,"weight_gb":58,"kv_cache_gb":42,"vram_gb":96,"ram_gb":11,"disk_gb":106,"requirement_source":67,"confidence":68},{"scenario":70,"context_length":71,"batch_size":35,"weight_gb":58,"kv_cache_gb":42,"vram_gb":108,"ram_gb":11,"disk_gb":109,"requirement_source":67,"confidence":68},{"scenario":75,"context_length":76,"batch_size":77,"weight_gb":58,"kv_cache_gb":42,"vram_gb":102,"ram_gb":11,"disk_gb":111,"requirement_source":67,"confidence":68},{"recommended":117,"cheapest":134,"performance":147,"min_complexity":158,"cluster_options":166,"no_match":167,"required_vram_gb":102,"candidate_count":168,"usage":169},{"gpu_model":118,"gpu_model_id":119,"gpu_count":41,"total_vram_gb":45,"hour_price":120,"monthly_cost":121,"providers":122,"bandwidth_gbps":124,"fp16_tflops":119,"interconnect_score":125,"parallel_efficiency":41,"score":126,"tier":127,"perf_metric":128,"perf_label":129,"perf_value":130,"workload":16,"cost_metric":131},"RTX 5060 Ti",24,0.1072,78.26,[123],"vast",448,40,0.5382,"cheapest","vectors\u002Fs","44800 vec\u002Fs",44800,{"effective_value":132,"effective_unit":128,"capacity_factor":133},35840,0.8,{"gpu_model":135,"gpu_model_id":136,"gpu_count":41,"total_vram_gb":45,"hour_price":137,"monthly_cost":138,"providers":139,"bandwidth_gbps":140,"fp16_tflops":141,"interconnect_score":125,"parallel_efficiency":41,"score":142,"tier":127,"perf_metric":128,"perf_label":143,"perf_value":144,"workload":16,"cost_metric":145},"RTX 4060 Ti",29,0.0811,59.2,[123],288,45,0.5375,"28800 vec\u002Fs",28800,{"effective_value":146,"effective_unit":128,"capacity_factor":133},23040,{"gpu_model":118,"gpu_model_id":119,"gpu_count":45,"total_vram_gb":148,"hour_price":120,"monthly_cost":149,"providers":150,"bandwidth_gbps":124,"fp16_tflops":119,"interconnect_score":125,"parallel_efficiency":151,"score":152,"tier":153,"perf_metric":128,"perf_label":154,"perf_value":155,"workload":16,"cost_metric":156},64,626.05,[123],0.4,0.3572,"balanced","358400 vec\u002Fs",358400,{"effective_value":157,"effective_unit":128,"capacity_factor":133},286720,{"gpu_model":135,"gpu_model_id":136,"gpu_count":77,"total_vram_gb":40,"hour_price":137,"monthly_cost":159,"providers":160,"bandwidth_gbps":140,"fp16_tflops":141,"interconnect_score":125,"parallel_efficiency":133,"score":161,"tier":127,"perf_metric":128,"perf_label":162,"perf_value":163,"workload":16,"cost_metric":164},118.41,[123],0.4483,"57600 vec\u002Fs",57600,{"effective_value":165,"effective_unit":128,"capacity_factor":133},46080,[],false,6,"value",[171,178,183,192,200],{"name":172,"vram_gb":40,"cheapest_hour":173,"cost":174,"provider":123,"estimated_tps":42},"Tesla V100",0.0489,{"hourly":173,"daily":175,"monthly":176,"yearly":177},1.17,35.7,428.36,{"name":135,"vram_gb":45,"cheapest_hour":137,"cost":179,"provider":123,"estimated_tps":182},{"hourly":137,"daily":180,"monthly":138,"yearly":181},1.95,710.44,14400,{"name":184,"vram_gb":185,"cheapest_hour":186,"cost":187,"provider":123,"estimated_tps":191},"RTX 3080",10,0.0874,{"hourly":186,"daily":188,"monthly":189,"yearly":190},2.1,63.8,765.62,38000,{"name":193,"vram_gb":119,"cheapest_hour":194,"cost":195,"provider":123,"estimated_tps":199},"L4",0.1044,{"hourly":194,"daily":196,"monthly":197,"yearly":198},2.51,76.21,914.54,15000,{"name":118,"vram_gb":45,"cheapest_hour":120,"cost":201,"provider":123,"estimated_tps":204},{"hourly":120,"daily":202,"monthly":121,"yearly":203},2.57,939.07,22400,{"posts_count":42,"benchmarks_count":42}]