[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-qwen25-coder-3b":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":28,"variants":29,"quantizations":30,"requirements":57,"gpu_recommendations":138,"fitting_gpus":206,"community":241},315,"qwen25-coder-3b","Qwen2.5-Coder 3B","Qwen\u002FQwen2.5-Coder-3B-Instruct","Qwen","transformer",null,3100000000,"3.1B",131072,"MIT",111804,123,"published","https:\u002F\u002Fhuggingface.co\u002FQwen\u002FQwen2.5-Coder-3B-Instruct","2026-08-12T03:11:22+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":8,"slug":27},"qwen",0.2515,[],[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":82,"INT8":95,"AWQ":99,"GPTQ":112,"GGUF":125},{"minimum":59,"production":68,"recommended":75},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":62,"kv_cache_gb":44,"vram_gb":63,"ram_gb":64,"disk_gb":65,"requirement_source":66,"confidence":67},"minimum",4096,5.77,12.25,32,48.01,"estimated",0.95,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":62,"kv_cache_gb":71,"vram_gb":72,"ram_gb":73,"disk_gb":74,"requirement_source":66,"confidence":67},"production",16384,64,125.57,188.35,113.01,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":62,"kv_cache_gb":43,"vram_gb":79,"ram_gb":80,"disk_gb":81,"requirement_source":66,"confidence":67},"recommended",8192,2,28.34,42.5,74.01,{"minimum":83,"production":87,"recommended":91},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":84,"kv_cache_gb":44,"vram_gb":85,"ram_gb":64,"disk_gb":86,"requirement_source":66,"confidence":67},2.89,8.6,43.5,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":84,"kv_cache_gb":71,"vram_gb":88,"ram_gb":89,"disk_gb":90,"requirement_source":66,"confidence":67},121.58,182.38,108.5,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":84,"kv_cache_gb":43,"vram_gb":92,"ram_gb":93,"disk_gb":94,"requirement_source":66,"confidence":67},24.52,36.78,69.5,{"minimum":96,"production":97,"recommended":98},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":84,"kv_cache_gb":44,"vram_gb":85,"ram_gb":64,"disk_gb":86,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":84,"kv_cache_gb":71,"vram_gb":88,"ram_gb":89,"disk_gb":90,"requirement_source":66,"confidence":67},{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":84,"kv_cache_gb":43,"vram_gb":92,"ram_gb":93,"disk_gb":94,"requirement_source":66,"confidence":67},{"minimum":100,"production":104,"recommended":108},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":101,"kv_cache_gb":44,"vram_gb":102,"ram_gb":64,"disk_gb":103,"requirement_source":66,"confidence":67},1.5,6.84,41.34,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":101,"kv_cache_gb":71,"vram_gb":105,"ram_gb":106,"disk_gb":107,"requirement_source":66,"confidence":67},119.67,179.5,106.34,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":101,"kv_cache_gb":43,"vram_gb":109,"ram_gb":110,"disk_gb":111,"requirement_source":66,"confidence":67},22.68,34.02,67.34,{"minimum":113,"production":117,"recommended":121},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":114,"kv_cache_gb":44,"vram_gb":115,"ram_gb":64,"disk_gb":116,"requirement_source":66,"confidence":67},1.52,6.87,41.36,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":114,"kv_cache_gb":71,"vram_gb":118,"ram_gb":119,"disk_gb":120,"requirement_source":66,"confidence":67},119.69,179.54,106.36,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":114,"kv_cache_gb":43,"vram_gb":122,"ram_gb":123,"disk_gb":124,"requirement_source":66,"confidence":67},22.7,34.06,67.36,{"minimum":126,"production":130,"recommended":134},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":127,"kv_cache_gb":44,"vram_gb":128,"ram_gb":64,"disk_gb":129,"requirement_source":66,"confidence":67},1.55,6.91,41.42,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":127,"kv_cache_gb":71,"vram_gb":131,"ram_gb":132,"disk_gb":133,"requirement_source":66,"confidence":67},119.74,179.61,106.42,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":127,"kv_cache_gb":43,"vram_gb":135,"ram_gb":136,"disk_gb":137,"requirement_source":66,"confidence":67},22.75,34.13,67.42,{"recommended":139,"cheapest":157,"performance":172,"min_complexity":189,"cluster_options":203,"no_match":204,"required_vram_gb":109,"candidate_count":160,"usage":205},{"gpu_model":140,"gpu_model_id":78,"gpu_count":39,"total_vram_gb":64,"hour_price":141,"monthly_cost":142,"providers":143,"bandwidth_gbps":146,"fp16_tflops":147,"interconnect_score":148,"parallel_efficiency":39,"score":149,"tier":150,"perf_metric":151,"perf_label":152,"perf_value":153,"workload":10,"cost_metric":154},"RTX 5090",0.337,246.01,[144,145],"vast","runpod",1792,209,40,0.6867,"cheapest","tok\u002Fs","1194.7 tok\u002Fs",1194.7,{"effective_value":155,"effective_unit":151,"capacity_factor":156},836.3,0.7,{"gpu_model":158,"gpu_model_id":159,"gpu_count":78,"total_vram_gb":160,"hour_price":161,"monthly_cost":162,"providers":163,"bandwidth_gbps":164,"fp16_tflops":165,"interconnect_score":148,"parallel_efficiency":166,"score":167,"tier":150,"perf_metric":151,"perf_label":168,"perf_value":169,"workload":10,"cost_metric":170},"RTX 5070",28,24,0.0101,14.75,[144],672,61,0.8,0.6029,"716.8 tok\u002Fs",716.8,{"effective_value":171,"effective_unit":151,"capacity_factor":156},501.8,{"gpu_model":173,"gpu_model_id":174,"gpu_count":43,"total_vram_gb":175,"hour_price":176,"monthly_cost":177,"providers":178,"bandwidth_gbps":180,"fp16_tflops":181,"interconnect_score":148,"parallel_efficiency":182,"score":183,"tier":184,"perf_metric":151,"perf_label":185,"perf_value":186,"workload":10,"cost_metric":187},"H200 SXM",11,1128,3.5,20440,[179],"lambda",4800,989,0.4,0.2197,"balanced","10240 tok\u002Fs",10240,{"effective_value":188,"effective_unit":151,"capacity_factor":156},7168,{"gpu_model":190,"gpu_model_id":191,"gpu_count":39,"total_vram_gb":160,"hour_price":192,"monthly_cost":193,"providers":194,"bandwidth_gbps":196,"fp16_tflops":197,"interconnect_score":148,"parallel_efficiency":39,"score":198,"tier":150,"perf_metric":151,"perf_label":199,"perf_value":200,"workload":10,"cost_metric":201},"RTX 3090",3,0.0678,49.49,[144,195],"tensordock",936,71,0.6437,"624 tok\u002Fs",624,{"effective_value":202,"effective_unit":151,"capacity_factor":156},436.8,[],false,"value",[207,211,218,225,233],{"name":190,"vram_gb":160,"cheapest_hour":192,"cost":208,"provider":144,"estimated_tps":200},{"hourly":192,"daily":209,"monthly":193,"yearly":210},1.63,593.93,{"name":212,"vram_gb":160,"cheapest_hour":213,"cost":214,"provider":144,"estimated_tps":164},"RTX 4090",0.1344,{"hourly":213,"daily":215,"monthly":216,"yearly":217},3.23,98.11,1177.34,{"name":219,"vram_gb":160,"cheapest_hour":220,"cost":221,"provider":144,"estimated_tps":164},"RTX 4090D",0.1602,{"hourly":220,"daily":222,"monthly":223,"yearly":224},3.84,116.95,1403.35,{"name":226,"vram_gb":160,"cheapest_hour":227,"cost":228,"provider":144,"estimated_tps":232},"A10",0.2015,{"hourly":227,"daily":229,"monthly":230,"yearly":231},4.84,147.1,1765.14,400,{"name":234,"vram_gb":160,"cheapest_hour":235,"cost":236,"provider":144,"estimated_tps":240},"L4",0.2022,{"hourly":235,"daily":237,"monthly":238,"yearly":239},4.85,147.61,1771.27,200,{"posts_count":40,"benchmarks_count":40}]