[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-yi-coder-9b":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":26,"score":29,"variants":30,"quantizations":31,"requirements":58,"gpu_recommendations":140,"fitting_gpus":204,"community":235},417,"yi-coder-9b","Yi-Coder 9B","01-ai\u002FYi-Coder-9B","01-ai","transformer",null,8800000000,"8.8B",131072,"MIT",7753,46,"published","https:\u002F\u002Fhuggingface.co\u002F01-ai\u002FYi-Coder-9B","2026-08-12T03:11:28+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",{"name":27,"slug":28},"Yi","yi",0.0005,[],[32,37,42,47,51,55],{"format":33,"bits":34,"size_factor":35,"quality_loss":36},"AWQ",4,0.263,0.03,{"format":38,"bits":39,"size_factor":40,"quality_loss":41},"FP16",16,1,0,{"format":43,"bits":44,"size_factor":45,"quality_loss":46},"FP8",8,0.5,0.01,{"format":48,"bits":34,"size_factor":49,"quality_loss":50},"GGUF",0.25,0.05,{"format":52,"bits":34,"size_factor":53,"quality_loss":54},"GPTQ",0.275,0.04,{"format":56,"bits":44,"size_factor":45,"quality_loss":57},"INT8",0.02,{"FP16":59,"FP8":83,"INT8":97,"AWQ":101,"GPTQ":114,"GGUF":127},{"minimum":60,"production":69,"recommended":76},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":63,"kv_cache_gb":45,"vram_gb":64,"ram_gb":65,"disk_gb":66,"requirement_source":67,"confidence":68},"minimum",4096,16.39,25.68,38.53,64.57,"estimated",0.95,{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":63,"kv_cache_gb":72,"vram_gb":73,"ram_gb":74,"disk_gb":75,"requirement_source":67,"confidence":68},"production",16384,64,140.22,210.33,129.57,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":63,"kv_cache_gb":44,"vram_gb":80,"ram_gb":81,"disk_gb":82,"requirement_source":67,"confidence":68},"recommended",8192,2,42.38,63.57,90.57,{"minimum":84,"production":89,"recommended":93},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":85,"kv_cache_gb":45,"vram_gb":86,"ram_gb":87,"disk_gb":88,"requirement_source":67,"confidence":68},8.2,15.32,32,51.79,{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":85,"kv_cache_gb":72,"vram_gb":90,"ram_gb":91,"disk_gb":92,"requirement_source":67,"confidence":68},128.91,193.36,116.79,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":85,"kv_cache_gb":44,"vram_gb":94,"ram_gb":95,"disk_gb":96,"requirement_source":67,"confidence":68},31.54,47.31,77.79,{"minimum":98,"production":99,"recommended":100},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":85,"kv_cache_gb":45,"vram_gb":86,"ram_gb":87,"disk_gb":88,"requirement_source":67,"confidence":68},{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":85,"kv_cache_gb":72,"vram_gb":90,"ram_gb":91,"disk_gb":92,"requirement_source":67,"confidence":68},{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":85,"kv_cache_gb":44,"vram_gb":94,"ram_gb":95,"disk_gb":96,"requirement_source":67,"confidence":68},{"minimum":102,"production":106,"recommended":110},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":103,"kv_cache_gb":45,"vram_gb":104,"ram_gb":87,"disk_gb":105,"requirement_source":67,"confidence":68},4.25,10.33,45.63,{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":103,"kv_cache_gb":72,"vram_gb":107,"ram_gb":108,"disk_gb":109,"requirement_source":67,"confidence":68},123.47,185.2,110.63,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":103,"kv_cache_gb":44,"vram_gb":111,"ram_gb":112,"disk_gb":113,"requirement_source":67,"confidence":68},26.32,39.48,71.63,{"minimum":115,"production":119,"recommended":123},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":116,"kv_cache_gb":45,"vram_gb":117,"ram_gb":87,"disk_gb":118,"requirement_source":67,"confidence":68},4.3,10.39,45.71,{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":116,"kv_cache_gb":72,"vram_gb":120,"ram_gb":121,"disk_gb":122,"requirement_source":67,"confidence":68},123.54,185.31,110.71,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":116,"kv_cache_gb":44,"vram_gb":124,"ram_gb":125,"disk_gb":126,"requirement_source":67,"confidence":68},26.39,39.59,71.71,{"minimum":128,"production":132,"recommended":136},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":129,"kv_cache_gb":45,"vram_gb":130,"ram_gb":87,"disk_gb":131,"requirement_source":67,"confidence":68},4.41,10.52,45.87,{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":129,"kv_cache_gb":72,"vram_gb":133,"ram_gb":134,"disk_gb":135,"requirement_source":67,"confidence":68},123.68,185.52,110.87,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":129,"kv_cache_gb":44,"vram_gb":137,"ram_gb":138,"disk_gb":139,"requirement_source":67,"confidence":68},26.53,39.79,71.87,{"recommended":141,"cheapest":159,"performance":169,"min_complexity":186,"cluster_options":200,"no_match":201,"required_vram_gb":111,"candidate_count":202,"usage":203},{"gpu_model":142,"gpu_model_id":79,"gpu_count":40,"total_vram_gb":87,"hour_price":143,"monthly_cost":144,"providers":145,"bandwidth_gbps":148,"fp16_tflops":149,"interconnect_score":150,"parallel_efficiency":40,"score":151,"tier":152,"perf_metric":153,"perf_label":154,"perf_value":155,"workload":10,"cost_metric":156},"RTX 5090",0.3222,235.21,[146,147],"vast","runpod",1792,209,40,0.6786,"cheapest","tok\u002Fs","421.6 tok\u002Fs",421.6,{"effective_value":157,"effective_unit":153,"capacity_factor":158},295.1,0.7,{"gpu_model":160,"gpu_model_id":161,"gpu_count":79,"total_vram_gb":87,"hour_price":162,"monthly_cost":163,"providers":164,"bandwidth_gbps":41,"fp16_tflops":41,"interconnect_score":150,"parallel_efficiency":165,"score":166,"tier":152,"perf_metric":153,"perf_label":167,"perf_value":41,"workload":10,"cost_metric":168},"Tesla V100",17,0.0272,39.71,[146],0.8,0.6273,"0 tok\u002Fs",{"effective_value":41,"effective_unit":153,"capacity_factor":158},{"gpu_model":170,"gpu_model_id":171,"gpu_count":44,"total_vram_gb":172,"hour_price":173,"monthly_cost":174,"providers":175,"bandwidth_gbps":177,"fp16_tflops":178,"interconnect_score":150,"parallel_efficiency":179,"score":180,"tier":181,"perf_metric":153,"perf_label":182,"perf_value":183,"workload":10,"cost_metric":184},"H200 SXM",11,1128,3.5,20440,[176],"lambda",4800,989,0.4,0.2197,"balanced","3614.1 tok\u002Fs",3614.1,{"effective_value":185,"effective_unit":153,"capacity_factor":158},2529.9,{"gpu_model":187,"gpu_model_id":188,"gpu_count":40,"total_vram_gb":189,"hour_price":190,"monthly_cost":191,"providers":192,"bandwidth_gbps":193,"fp16_tflops":194,"interconnect_score":150,"parallel_efficiency":40,"score":195,"tier":152,"perf_metric":153,"perf_label":196,"perf_value":197,"workload":10,"cost_metric":198},"RTX A6000",6,48,0.3001,219.07,[146,176],768,77,0.6371,"180.7 tok\u002Fs",180.7,{"effective_value":199,"effective_unit":153,"capacity_factor":158},126.5,[],false,24,"value",[205,209,213,221,228],{"name":187,"vram_gb":189,"cheapest_hour":190,"cost":206,"provider":146,"estimated_tps":197},{"hourly":190,"daily":207,"monthly":191,"yearly":208},7.2,2628.88,{"name":142,"vram_gb":87,"cheapest_hour":143,"cost":210,"provider":146,"estimated_tps":155},{"hourly":143,"daily":211,"monthly":144,"yearly":212},7.73,2822.47,{"name":214,"vram_gb":189,"cheapest_hour":215,"cost":216,"provider":146,"estimated_tps":220},"L40S",0.4669,{"hourly":215,"daily":217,"monthly":218,"yearly":219},11.21,340.84,4090.04,203.3,{"name":222,"vram_gb":189,"cheapest_hour":223,"cost":224,"provider":146,"estimated_tps":41},"RTX PRO 6000 WS",0.8022,{"hourly":223,"daily":225,"monthly":226,"yearly":227},19.25,585.61,7027.27,{"name":229,"vram_gb":189,"cheapest_hour":230,"cost":231,"provider":146,"estimated_tps":41},"RTX PRO 6000 S",1.0131,{"hourly":230,"daily":232,"monthly":233,"yearly":234},24.31,739.56,8874.76,{"posts_count":41,"benchmarks_count":41}]