[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-santacoder-11b":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":10,"huggingface_url":18,"created_at":19,"seo":20,"category":23,"family":10,"score":26,"variants":27,"quantizations":28,"requirements":55,"gpu_recommendations":136,"fitting_gpus":201,"community":237},359,"santacoder-11b","SantaCoder 1.1B","bigcode\u002Fsantacoder","bigcode","transformer",null,1100000000,"1.1B",2048,"MIT",4770,336,"published","https:\u002F\u002Fhuggingface.co\u002Fbigcode\u002Fsantacoder","2026-08-12T03:11:25+00:00",{"title":6,"description":21,"image":10,"robots":22,"canonical_url":10},"AI 模型部署决策引擎——开源 AI 的 GPU 需求、云端价格与成本分析。","index, follow",{"name":24,"slug":25},"Coding AI","coding",0.0037,[],[29,34,39,44,48,52],{"format":30,"bits":31,"size_factor":32,"quality_loss":33},"AWQ",4,0.263,0.03,{"format":35,"bits":36,"size_factor":37,"quality_loss":38},"FP16",16,1,0,{"format":40,"bits":41,"size_factor":42,"quality_loss":43},"FP8",8,0.5,0.01,{"format":45,"bits":31,"size_factor":46,"quality_loss":47},"GGUF",0.25,0.05,{"format":49,"bits":31,"size_factor":50,"quality_loss":51},"GPTQ",0.275,0.04,{"format":53,"bits":41,"size_factor":42,"quality_loss":54},"INT8",0.02,{"FP16":56,"FP8":80,"INT8":93,"AWQ":97,"GPTQ":110,"GGUF":123},{"minimum":57,"production":66,"recommended":73},{"scenario":58,"context_length":59,"batch_size":37,"weight_gb":60,"kv_cache_gb":42,"vram_gb":61,"ram_gb":62,"disk_gb":63,"requirement_source":64,"confidence":65},"minimum",4096,2.05,7.54,32,42.2,"estimated",0.95,{"scenario":67,"context_length":68,"batch_size":31,"weight_gb":60,"kv_cache_gb":69,"vram_gb":70,"ram_gb":71,"disk_gb":72,"requirement_source":64,"confidence":65},"production",16384,64,120.43,180.64,107.2,{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":60,"kv_cache_gb":41,"vram_gb":77,"ram_gb":78,"disk_gb":79,"requirement_source":64,"confidence":65},"recommended",8192,2,23.41,35.11,68.2,{"minimum":81,"production":85,"recommended":89},{"scenario":58,"context_length":59,"batch_size":37,"weight_gb":82,"kv_cache_gb":42,"vram_gb":83,"ram_gb":62,"disk_gb":84,"requirement_source":64,"confidence":65},1.02,6.25,40.6,{"scenario":67,"context_length":68,"batch_size":31,"weight_gb":82,"kv_cache_gb":69,"vram_gb":86,"ram_gb":87,"disk_gb":88,"requirement_source":64,"confidence":65},119.01,178.52,105.6,{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":82,"kv_cache_gb":41,"vram_gb":90,"ram_gb":91,"disk_gb":92,"requirement_source":64,"confidence":65},22.05,33.08,66.6,{"minimum":94,"production":95,"recommended":96},{"scenario":58,"context_length":59,"batch_size":37,"weight_gb":82,"kv_cache_gb":42,"vram_gb":83,"ram_gb":62,"disk_gb":84,"requirement_source":64,"confidence":65},{"scenario":67,"context_length":68,"batch_size":31,"weight_gb":82,"kv_cache_gb":69,"vram_gb":86,"ram_gb":87,"disk_gb":88,"requirement_source":64,"confidence":65},{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":82,"kv_cache_gb":41,"vram_gb":90,"ram_gb":91,"disk_gb":92,"requirement_source":64,"confidence":65},{"minimum":98,"production":102,"recommended":106},{"scenario":58,"context_length":59,"batch_size":37,"weight_gb":99,"kv_cache_gb":42,"vram_gb":100,"ram_gb":62,"disk_gb":101,"requirement_source":64,"confidence":65},0.53,5.62,39.83,{"scenario":67,"context_length":68,"batch_size":31,"weight_gb":99,"kv_cache_gb":69,"vram_gb":103,"ram_gb":104,"disk_gb":105,"requirement_source":64,"confidence":65},118.33,177.5,104.83,{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":99,"kv_cache_gb":41,"vram_gb":107,"ram_gb":108,"disk_gb":109,"requirement_source":64,"confidence":65},21.4,32.1,65.83,{"minimum":111,"production":115,"recommended":119},{"scenario":58,"context_length":59,"batch_size":37,"weight_gb":112,"kv_cache_gb":42,"vram_gb":113,"ram_gb":62,"disk_gb":114,"requirement_source":64,"confidence":65},0.54,5.63,39.84,{"scenario":67,"context_length":68,"batch_size":31,"weight_gb":112,"kv_cache_gb":69,"vram_gb":116,"ram_gb":117,"disk_gb":118,"requirement_source":64,"confidence":65},118.34,177.51,104.84,{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":112,"kv_cache_gb":41,"vram_gb":120,"ram_gb":121,"disk_gb":122,"requirement_source":64,"confidence":65},21.41,32.12,65.84,{"minimum":124,"production":128,"recommended":132},{"scenario":58,"context_length":59,"batch_size":37,"weight_gb":125,"kv_cache_gb":42,"vram_gb":126,"ram_gb":62,"disk_gb":127,"requirement_source":64,"confidence":65},0.55,5.65,39.86,{"scenario":67,"context_length":68,"batch_size":31,"weight_gb":125,"kv_cache_gb":69,"vram_gb":129,"ram_gb":130,"disk_gb":131,"requirement_source":64,"confidence":65},118.36,177.54,104.86,{"scenario":74,"context_length":75,"batch_size":76,"weight_gb":125,"kv_cache_gb":41,"vram_gb":133,"ram_gb":134,"disk_gb":135,"requirement_source":64,"confidence":65},21.43,32.14,65.86,{"recommended":137,"cheapest":155,"performance":165,"min_complexity":182,"cluster_options":197,"no_match":198,"required_vram_gb":107,"candidate_count":199,"usage":200},{"gpu_model":138,"gpu_model_id":76,"gpu_count":37,"total_vram_gb":62,"hour_price":139,"monthly_cost":140,"providers":141,"bandwidth_gbps":144,"fp16_tflops":145,"interconnect_score":146,"parallel_efficiency":37,"score":147,"tier":148,"perf_metric":149,"perf_label":150,"perf_value":151,"workload":10,"cost_metric":152},"RTX 5090",0.3222,235.21,[142,143],"vast","runpod",1792,209,40,0.6762,"cheapest","tok\u002Fs","3381.1 tok\u002Fs",3381.1,{"effective_value":153,"effective_unit":149,"capacity_factor":154},2366.8,0.7,{"gpu_model":156,"gpu_model_id":157,"gpu_count":76,"total_vram_gb":62,"hour_price":158,"monthly_cost":159,"providers":160,"bandwidth_gbps":38,"fp16_tflops":38,"interconnect_score":146,"parallel_efficiency":161,"score":162,"tier":148,"perf_metric":149,"perf_label":163,"perf_value":38,"workload":10,"cost_metric":164},"Tesla V100",17,0.0272,39.71,[142],0.8,0.625,"0 tok\u002Fs",{"effective_value":38,"effective_unit":149,"capacity_factor":154},{"gpu_model":166,"gpu_model_id":167,"gpu_count":41,"total_vram_gb":168,"hour_price":169,"monthly_cost":170,"providers":171,"bandwidth_gbps":173,"fp16_tflops":174,"interconnect_score":146,"parallel_efficiency":175,"score":176,"tier":177,"perf_metric":149,"perf_label":178,"perf_value":179,"workload":10,"cost_metric":180},"H200 SXM",11,1128,3.5,20440,[172],"lambda",4800,989,0.4,0.2197,"balanced","28981.1 tok\u002Fs",28981.1,{"effective_value":181,"effective_unit":149,"capacity_factor":154},20286.8,{"gpu_model":183,"gpu_model_id":184,"gpu_count":37,"total_vram_gb":185,"hour_price":186,"monthly_cost":187,"providers":188,"bandwidth_gbps":190,"fp16_tflops":191,"interconnect_score":146,"parallel_efficiency":37,"score":192,"tier":148,"perf_metric":149,"perf_label":193,"perf_value":194,"workload":10,"cost_metric":195},"RTX 3090",3,24,0.0678,49.49,[142,189],"tensordock",936,71,0.6579,"1766 tok\u002Fs",1766,{"effective_value":196,"effective_unit":149,"capacity_factor":154},1236.2,[],false,25,"value",[202,206,214,221,229],{"name":183,"vram_gb":185,"cheapest_hour":186,"cost":203,"provider":142,"estimated_tps":194},{"hourly":186,"daily":204,"monthly":187,"yearly":205},1.63,593.93,{"name":207,"vram_gb":185,"cheapest_hour":208,"cost":209,"provider":142,"estimated_tps":213},"RTX 4090",0.1344,{"hourly":208,"daily":210,"monthly":211,"yearly":212},3.23,98.11,1177.34,1901.9,{"name":215,"vram_gb":185,"cheapest_hour":216,"cost":217,"provider":142,"estimated_tps":213},"RTX 4090D",0.1602,{"hourly":216,"daily":218,"monthly":219,"yearly":220},3.84,116.95,1403.35,{"name":222,"vram_gb":185,"cheapest_hour":223,"cost":224,"provider":142,"estimated_tps":228},"L4",0.2015,{"hourly":223,"daily":225,"monthly":226,"yearly":227},4.84,147.1,1765.14,566,{"name":230,"vram_gb":185,"cheapest_hour":231,"cost":232,"provider":142,"estimated_tps":236},"A10",0.2409,{"hourly":231,"daily":233,"monthly":234,"yearly":235},5.78,175.86,2110.28,1132.1,{"posts_count":38,"benchmarks_count":38}]