[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-gemma-2-9b-it":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":18,"huggingface_url":19,"created_at":20,"seo":21,"category":23,"family":26,"score":28,"variants":29,"quantizations":30,"requirements":57,"gpu_recommendations":138,"fitting_gpus":204,"community":239},17,"gemma-2-9b-it","Gemma-2-9B-IT","google\u002Fgemma-2-9b-it","google","gemma",null,9200000000,"9.2B",8192,"gemma-license",1900000,3800,"published","Gemma 2 9B, widely used open model.","https:\u002F\u002Fhuggingface.co\u002Fgoogle\u002Fgemma-2-9b-it","2026-08-12T02:22:24+00:00",{"title":6,"description":18,"image":10,"robots":22,"canonical_url":10},"index, follow",{"name":24,"slug":25},"LLM","llm",{"name":27,"slug":9},"Gemma",0.045,[],[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":81,"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",4096,17.14,26.63,39.94,65.73,"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",16384,64,141.25,211.87,130.73,{"scenario":76,"context_length":13,"batch_size":77,"weight_gb":62,"kv_cache_gb":43,"vram_gb":78,"ram_gb":79,"disk_gb":80,"requirement_source":66,"confidence":67},"recommended",2,43.36,65.04,91.73,{"minimum":82,"production":87,"recommended":91},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":83,"kv_cache_gb":44,"vram_gb":84,"ram_gb":85,"disk_gb":86,"requirement_source":66,"confidence":67},8.57,15.79,32,52.37,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":83,"kv_cache_gb":71,"vram_gb":88,"ram_gb":89,"disk_gb":90,"requirement_source":66,"confidence":67},129.42,194.14,117.37,{"scenario":76,"context_length":13,"batch_size":77,"weight_gb":83,"kv_cache_gb":43,"vram_gb":92,"ram_gb":93,"disk_gb":94,"requirement_source":66,"confidence":67},32.03,48.05,78.37,{"minimum":96,"production":97,"recommended":98},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":83,"kv_cache_gb":44,"vram_gb":84,"ram_gb":85,"disk_gb":86,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":83,"kv_cache_gb":71,"vram_gb":88,"ram_gb":89,"disk_gb":90,"requirement_source":66,"confidence":67},{"scenario":76,"context_length":13,"batch_size":77,"weight_gb":83,"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":85,"disk_gb":103,"requirement_source":66,"confidence":67},4.44,10.57,45.93,{"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},123.73,185.6,110.93,{"scenario":76,"context_length":13,"batch_size":77,"weight_gb":101,"kv_cache_gb":43,"vram_gb":109,"ram_gb":110,"disk_gb":111,"requirement_source":66,"confidence":67},26.58,39.87,71.93,{"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":85,"disk_gb":116,"requirement_source":66,"confidence":67},4.5,10.64,46.02,{"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},123.81,185.71,111.02,{"scenario":76,"context_length":13,"batch_size":77,"weight_gb":114,"kv_cache_gb":43,"vram_gb":122,"ram_gb":123,"disk_gb":124,"requirement_source":66,"confidence":67},26.65,39.97,72.02,{"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":85,"disk_gb":129,"requirement_source":66,"confidence":67},4.61,10.78,46.18,{"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},123.96,185.93,111.18,{"scenario":76,"context_length":13,"batch_size":77,"weight_gb":127,"kv_cache_gb":43,"vram_gb":135,"ram_gb":136,"disk_gb":137,"requirement_source":66,"confidence":67},26.79,40.19,72.18,{"recommended":139,"cheapest":161,"performance":171,"min_complexity":186,"cluster_options":200,"no_match":201,"required_vram_gb":109,"candidate_count":202,"usage":203},{"gpu_model":140,"gpu_model_id":141,"gpu_count":39,"total_vram_gb":142,"hour_price":143,"monthly_cost":144,"providers":145,"bandwidth_gbps":150,"fp16_tflops":151,"interconnect_score":152,"parallel_efficiency":39,"score":153,"tier":154,"perf_metric":155,"perf_label":156,"perf_value":157,"workload":10,"cost_metric":158},"H100 SXM",10,80,1.6022,1169.61,[146,147,148,149],"vast","tensordock","lambda","runpod",3350,66.9,40,0.5782,"balanced","tok\u002Fs","754.5 tok\u002Fs",754.5,{"effective_value":159,"effective_unit":155,"capacity_factor":160},528.2,0.7,{"gpu_model":162,"gpu_model_id":4,"gpu_count":77,"total_vram_gb":85,"hour_price":163,"monthly_cost":164,"providers":165,"bandwidth_gbps":40,"fp16_tflops":40,"interconnect_score":152,"parallel_efficiency":166,"score":167,"tier":168,"perf_metric":155,"perf_label":169,"perf_value":40,"workload":10,"cost_metric":170},"Tesla V100",0.0272,39.71,[146],0.8,0.6252,"cheapest","0 tok\u002Fs",{"effective_value":40,"effective_unit":155,"capacity_factor":160},{"gpu_model":172,"gpu_model_id":173,"gpu_count":43,"total_vram_gb":174,"hour_price":175,"monthly_cost":176,"providers":177,"bandwidth_gbps":178,"fp16_tflops":179,"interconnect_score":152,"parallel_efficiency":180,"score":181,"tier":154,"perf_metric":155,"perf_label":182,"perf_value":183,"workload":10,"cost_metric":184},"H200 SXM",11,1128,3.5,20440,[148],4800,989,0.4,0.2197,"3459.5 tok\u002Fs",3459.5,{"effective_value":185,"effective_unit":155,"capacity_factor":160},2421.6,{"gpu_model":187,"gpu_model_id":188,"gpu_count":39,"total_vram_gb":189,"hour_price":190,"monthly_cost":191,"providers":192,"bandwidth_gbps":193,"fp16_tflops":194,"interconnect_score":152,"parallel_efficiency":39,"score":195,"tier":168,"perf_metric":155,"perf_label":196,"perf_value":197,"workload":10,"cost_metric":198},"RTX A6000",6,48,0.3001,219.07,[146,148],768,77,0.6386,"173 tok\u002Fs",173,{"effective_value":199,"effective_unit":155,"capacity_factor":160},121.1,[],false,24,"value",[205,209,217,225,232],{"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":210,"vram_gb":85,"cheapest_hour":211,"cost":212,"provider":146,"estimated_tps":216},"RTX 5090",0.3222,{"hourly":211,"daily":213,"monthly":214,"yearly":215},7.73,235.21,2822.47,403.6,{"name":218,"vram_gb":189,"cheapest_hour":219,"cost":220,"provider":146,"estimated_tps":224},"L40S",0.4669,{"hourly":219,"daily":221,"monthly":222,"yearly":223},11.21,340.84,4090.04,194.6,{"name":226,"vram_gb":189,"cheapest_hour":227,"cost":228,"provider":146,"estimated_tps":40},"RTX PRO 6000 WS",0.8022,{"hourly":227,"daily":229,"monthly":230,"yearly":231},19.25,585.61,7027.27,{"name":233,"vram_gb":189,"cheapest_hour":234,"cost":235,"provider":146,"estimated_tps":40},"RTX PRO 6000 S",1.0131,{"hourly":234,"daily":236,"monthly":237,"yearly":238},24.31,739.56,8874.76,{"posts_count":40,"benchmarks_count":40}]