[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-qwen3-8b":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":20,"huggingface_url":21,"created_at":22,"seo":23,"category":25,"family":28,"score":30,"variants":31,"quantizations":32,"requirements":58,"gpu_recommendations":139,"fitting_gpus":203,"community":234},8,"qwen3-8b","Qwen\u002FQwen3-8B","Qwen","qwen3",{"layers":10,"head_dim":11,"kv_heads":4,"hidden_size":12},36,128,4096,7870087168,"7.9B",40960,null,16307008,1296,"published","Lightweight 8B model ideal for edge deployment and cheap cloud GPUs.","https:\u002F\u002Fhuggingface.co\u002FQwen\u002FQwen3-8B","2026-08-12T02:22:23+00:00",{"title":6,"description":20,"image":16,"robots":24,"canonical_url":16},"index, follow",{"name":26,"slug":27},"LLM","llm",{"name":7,"slug":29},"qwen",0.0399,[],[33,38,43,47,51,55],{"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":4,"size_factor":45,"quality_loss":46},"FP8",0.5,0.01,{"format":48,"bits":35,"size_factor":49,"quality_loss":50},"GGUF",0.25,0.05,{"format":52,"bits":35,"size_factor":53,"quality_loss":54},"GPTQ",0.275,0.04,{"format":56,"bits":4,"size_factor":45,"quality_loss":57},"INT8",0.02,{"FP16":59,"FP8":82,"INT8":96,"AWQ":100,"GPTQ":113,"GGUF":126},{"minimum":60,"production":68,"recommended":75},{"scenario":61,"context_length":12,"batch_size":41,"weight_gb":62,"kv_cache_gb":45,"vram_gb":63,"ram_gb":64,"disk_gb":65,"requirement_source":66,"confidence":67},"minimum",15.27,24.27,36.41,62.83,"estimated",0.95,{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":62,"kv_cache_gb":71,"vram_gb":72,"ram_gb":73,"disk_gb":74,"requirement_source":66,"confidence":67},"production",16384,64,138.68,208.02,127.83,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":62,"kv_cache_gb":4,"vram_gb":79,"ram_gb":80,"disk_gb":81,"requirement_source":66,"confidence":67},"recommended",8192,2,40.9,61.35,88.83,{"minimum":83,"production":88,"recommended":92},{"scenario":61,"context_length":12,"batch_size":41,"weight_gb":84,"kv_cache_gb":45,"vram_gb":85,"ram_gb":86,"disk_gb":87,"requirement_source":66,"confidence":67},7.64,14.61,32,50.91,{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":84,"kv_cache_gb":71,"vram_gb":89,"ram_gb":90,"disk_gb":91,"requirement_source":66,"confidence":67},128.14,192.21,115.91,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":84,"kv_cache_gb":4,"vram_gb":93,"ram_gb":94,"disk_gb":95,"requirement_source":66,"confidence":67},30.8,46.2,76.91,{"minimum":97,"production":98,"recommended":99},{"scenario":61,"context_length":12,"batch_size":41,"weight_gb":84,"kv_cache_gb":45,"vram_gb":85,"ram_gb":86,"disk_gb":87,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":84,"kv_cache_gb":71,"vram_gb":89,"ram_gb":90,"disk_gb":91,"requirement_source":66,"confidence":67},{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":84,"kv_cache_gb":4,"vram_gb":93,"ram_gb":94,"disk_gb":95,"requirement_source":66,"confidence":67},{"minimum":101,"production":105,"recommended":109},{"scenario":61,"context_length":12,"batch_size":41,"weight_gb":102,"kv_cache_gb":45,"vram_gb":103,"ram_gb":86,"disk_gb":104,"requirement_source":66,"confidence":67},3.96,9.96,45.18,{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":102,"kv_cache_gb":71,"vram_gb":106,"ram_gb":107,"disk_gb":108,"requirement_source":66,"confidence":67},123.07,184.6,110.18,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":102,"kv_cache_gb":4,"vram_gb":110,"ram_gb":111,"disk_gb":112,"requirement_source":66,"confidence":67},25.94,38.91,71.18,{"minimum":114,"production":118,"recommended":122},{"scenario":61,"context_length":12,"batch_size":41,"weight_gb":115,"kv_cache_gb":45,"vram_gb":116,"ram_gb":86,"disk_gb":117,"requirement_source":66,"confidence":67},4.01,10.02,45.25,{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":115,"kv_cache_gb":71,"vram_gb":119,"ram_gb":120,"disk_gb":121,"requirement_source":66,"confidence":67},123.13,184.7,110.25,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":115,"kv_cache_gb":4,"vram_gb":123,"ram_gb":124,"disk_gb":125,"requirement_source":66,"confidence":67},26,39,71.25,{"minimum":127,"production":131,"recommended":135},{"scenario":61,"context_length":12,"batch_size":41,"weight_gb":128,"kv_cache_gb":45,"vram_gb":129,"ram_gb":86,"disk_gb":130,"requirement_source":66,"confidence":67},4.1,10.14,45.4,{"scenario":69,"context_length":70,"batch_size":35,"weight_gb":128,"kv_cache_gb":71,"vram_gb":132,"ram_gb":133,"disk_gb":134,"requirement_source":66,"confidence":67},123.26,184.9,110.4,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":128,"kv_cache_gb":4,"vram_gb":136,"ram_gb":137,"disk_gb":138,"requirement_source":66,"confidence":67},26.13,39.19,71.4,{"recommended":140,"cheapest":158,"performance":168,"min_complexity":185,"cluster_options":199,"no_match":200,"required_vram_gb":110,"candidate_count":201,"usage":202},{"gpu_model":141,"gpu_model_id":78,"gpu_count":41,"total_vram_gb":86,"hour_price":142,"monthly_cost":143,"providers":144,"bandwidth_gbps":147,"fp16_tflops":148,"interconnect_score":149,"parallel_efficiency":41,"score":150,"tier":151,"perf_metric":152,"perf_label":153,"perf_value":154,"workload":16,"cost_metric":155},"RTX 5090",0.3222,235.21,[145,146],"vast","runpod",1792,209,40,0.6817,"cheapest","tok\u002Fs","452.5 tok\u002Fs",452.5,{"effective_value":156,"effective_unit":152,"capacity_factor":157},316.8,0.7,{"gpu_model":159,"gpu_model_id":160,"gpu_count":78,"total_vram_gb":86,"hour_price":161,"monthly_cost":162,"providers":163,"bandwidth_gbps":42,"fp16_tflops":42,"interconnect_score":149,"parallel_efficiency":164,"score":165,"tier":151,"perf_metric":152,"perf_label":166,"perf_value":42,"workload":16,"cost_metric":167},"Tesla V100",17,0.0272,39.71,[145],0.8,0.6305,"0 tok\u002Fs",{"effective_value":42,"effective_unit":152,"capacity_factor":157},{"gpu_model":169,"gpu_model_id":170,"gpu_count":4,"total_vram_gb":171,"hour_price":172,"monthly_cost":173,"providers":174,"bandwidth_gbps":176,"fp16_tflops":177,"interconnect_score":149,"parallel_efficiency":178,"score":179,"tier":180,"perf_metric":152,"perf_label":181,"perf_value":182,"workload":16,"cost_metric":183},"H200 SXM",11,1128,3.5,20440,[175],"lambda",4800,989,0.4,0.2197,"balanced","3878.8 tok\u002Fs",3878.8,{"effective_value":184,"effective_unit":152,"capacity_factor":157},2715.2,{"gpu_model":186,"gpu_model_id":187,"gpu_count":41,"total_vram_gb":188,"hour_price":189,"monthly_cost":190,"providers":191,"bandwidth_gbps":192,"fp16_tflops":193,"interconnect_score":149,"parallel_efficiency":41,"score":194,"tier":151,"perf_metric":152,"perf_label":195,"perf_value":196,"workload":16,"cost_metric":197},"RTX A6000",6,48,0.3001,219.07,[145,175],768,77,0.635,"193.9 tok\u002Fs",193.9,{"effective_value":198,"effective_unit":152,"capacity_factor":157},135.7,[],false,24,"value",[204,208,212,220,227],{"name":186,"vram_gb":188,"cheapest_hour":189,"cost":205,"provider":145,"estimated_tps":196},{"hourly":189,"daily":206,"monthly":190,"yearly":207},7.2,2628.88,{"name":141,"vram_gb":86,"cheapest_hour":142,"cost":209,"provider":145,"estimated_tps":154},{"hourly":142,"daily":210,"monthly":143,"yearly":211},7.73,2822.47,{"name":213,"vram_gb":188,"cheapest_hour":214,"cost":215,"provider":145,"estimated_tps":219},"L40S",0.4669,{"hourly":214,"daily":216,"monthly":217,"yearly":218},11.21,340.84,4090.04,218.2,{"name":221,"vram_gb":188,"cheapest_hour":222,"cost":223,"provider":145,"estimated_tps":42},"RTX PRO 6000 WS",0.8022,{"hourly":222,"daily":224,"monthly":225,"yearly":226},19.25,585.61,7027.27,{"name":228,"vram_gb":188,"cheapest_hour":229,"cost":230,"provider":145,"estimated_tps":42},"RTX PRO 6000 S",1.0131,{"hourly":229,"daily":231,"monthly":232,"yearly":233},24.31,739.56,8874.76,{"posts_count":42,"benchmarks_count":42}]