[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-mixtral-8x7b-instruct-v01":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":142,"fitting_gpus":208,"community":235},21,"mixtral-8x7b-instruct-v01","Mixtral-8x7B-Instruct-v0.1","mistralai\u002FMixtral-8x7B-Instruct-v0.1","mistralai","mixtral",null,46700000000,"46.7B",32768,"Apache-2.0",2000000,3400,"published","First-generation MoE (8x7B), efficient sparse inference.","https:\u002F\u002Fhuggingface.co\u002Fmistralai\u002FMixtral-8x7B-Instruct-v0.1","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},"Mixtral",0.1896,[],[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":96,"AWQ":100,"GPTQ":114,"GGUF":128},{"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",4096,86.99,114.99,172.48,174.7,"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",16384,64,237.64,356.46,239.7,{"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",8192,2,135.74,203.61,200.7,{"minimum":83,"production":88,"recommended":92},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":84,"kv_cache_gb":44,"vram_gb":85,"ram_gb":86,"disk_gb":87,"requirement_source":66,"confidence":67},43.49,59.97,89.95,106.85,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":84,"kv_cache_gb":71,"vram_gb":89,"ram_gb":90,"disk_gb":91,"requirement_source":66,"confidence":67},177.62,266.43,171.85,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":84,"kv_cache_gb":43,"vram_gb":93,"ram_gb":94,"disk_gb":95,"requirement_source":66,"confidence":67},78.22,117.33,132.85,{"minimum":97,"production":98,"recommended":99},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":84,"kv_cache_gb":44,"vram_gb":85,"ram_gb":86,"disk_gb":87,"requirement_source":66,"confidence":67},{"scenario":69,"context_length":70,"batch_size":33,"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":43,"vram_gb":93,"ram_gb":94,"disk_gb":95,"requirement_source":66,"confidence":67},{"minimum":101,"production":106,"recommended":110},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":102,"kv_cache_gb":44,"vram_gb":103,"ram_gb":104,"disk_gb":105,"requirement_source":66,"confidence":67},22.56,33.49,50.24,74.2,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":102,"kv_cache_gb":71,"vram_gb":107,"ram_gb":108,"disk_gb":109,"requirement_source":66,"confidence":67},148.74,223.1,139.2,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":102,"kv_cache_gb":43,"vram_gb":111,"ram_gb":112,"disk_gb":113,"requirement_source":66,"confidence":67},50.54,75.81,100.2,{"minimum":115,"production":120,"recommended":124},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":116,"kv_cache_gb":44,"vram_gb":117,"ram_gb":118,"disk_gb":119,"requirement_source":66,"confidence":67},22.83,33.83,50.75,74.62,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":116,"kv_cache_gb":71,"vram_gb":121,"ram_gb":122,"disk_gb":123,"requirement_source":66,"confidence":67},149.11,223.67,139.62,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":116,"kv_cache_gb":43,"vram_gb":125,"ram_gb":126,"disk_gb":127,"requirement_source":66,"confidence":67},50.9,76.35,100.62,{"minimum":129,"production":134,"recommended":138},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":130,"kv_cache_gb":44,"vram_gb":131,"ram_gb":132,"disk_gb":133,"requirement_source":66,"confidence":67},23.38,34.52,51.78,75.47,{"scenario":69,"context_length":70,"batch_size":33,"weight_gb":130,"kv_cache_gb":71,"vram_gb":135,"ram_gb":136,"disk_gb":137,"requirement_source":66,"confidence":67},149.86,224.79,140.47,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":130,"kv_cache_gb":43,"vram_gb":139,"ram_gb":140,"disk_gb":141,"requirement_source":66,"confidence":67},51.62,77.42,101.47,{"recommended":143,"cheapest":165,"performance":176,"min_complexity":191,"cluster_options":204,"no_match":205,"required_vram_gb":111,"candidate_count":206,"usage":207},{"gpu_model":144,"gpu_model_id":145,"gpu_count":39,"total_vram_gb":146,"hour_price":147,"monthly_cost":148,"providers":149,"bandwidth_gbps":154,"fp16_tflops":155,"interconnect_score":156,"parallel_efficiency":39,"score":157,"tier":158,"perf_metric":159,"perf_label":160,"perf_value":161,"workload":10,"cost_metric":162},"H100 SXM",10,80,1.6022,1169.61,[150,151,152,153],"vast","tensordock","lambda","runpod",3350,66.9,40,0.658,"balanced","tok\u002Fs","148.5 tok\u002Fs",148.5,{"effective_value":163,"effective_unit":159,"capacity_factor":164},103.9,0.7,{"gpu_model":166,"gpu_model_id":167,"gpu_count":33,"total_vram_gb":71,"hour_price":168,"monthly_cost":169,"providers":170,"bandwidth_gbps":40,"fp16_tflops":40,"interconnect_score":156,"parallel_efficiency":171,"score":172,"tier":173,"perf_metric":159,"perf_label":174,"perf_value":40,"workload":10,"cost_metric":175},"Tesla V100",17,0.0272,79.42,[150],0.6,0.5878,"cheapest","0 tok\u002Fs",{"effective_value":40,"effective_unit":159,"capacity_factor":164},{"gpu_model":177,"gpu_model_id":178,"gpu_count":43,"total_vram_gb":179,"hour_price":180,"monthly_cost":181,"providers":182,"bandwidth_gbps":183,"fp16_tflops":184,"interconnect_score":156,"parallel_efficiency":185,"score":186,"tier":158,"perf_metric":159,"perf_label":187,"perf_value":188,"workload":10,"cost_metric":189},"H200 SXM",11,1128,3.5,20440,[152],4800,989,0.4,0.2197,"680.9 tok\u002Fs",680.9,{"effective_value":190,"effective_unit":159,"capacity_factor":164},476.6,{"gpu_model":192,"gpu_model_id":193,"gpu_count":39,"total_vram_gb":146,"hour_price":194,"monthly_cost":195,"providers":196,"bandwidth_gbps":197,"fp16_tflops":198,"interconnect_score":156,"parallel_efficiency":39,"score":199,"tier":158,"perf_metric":159,"perf_label":200,"perf_value":201,"workload":10,"cost_metric":202},"A100 80GB",9,1.2,876,[150,151,153,152],2039,77.97,0.6548,"90.4 tok\u002Fs",90.4,{"effective_value":203,"effective_unit":159,"capacity_factor":164},63.3,[],false,20,"value",[209,213,217,224,232],{"name":192,"vram_gb":146,"cheapest_hour":194,"cost":210,"provider":150,"estimated_tps":201},{"hourly":194,"daily":211,"monthly":195,"yearly":212},28.8,10512,{"name":144,"vram_gb":146,"cheapest_hour":147,"cost":214,"provider":150,"estimated_tps":161},{"hourly":147,"daily":215,"monthly":148,"yearly":216},38.45,14035.27,{"name":177,"vram_gb":218,"cheapest_hour":180,"cost":219,"provider":152,"estimated_tps":223},141,{"hourly":180,"daily":220,"monthly":221,"yearly":222},84,2555,30660,212.8,{"name":225,"vram_gb":226,"cheapest_hour":227,"cost":228,"provider":150,"estimated_tps":40},"B200",180,4.1271,{"hourly":227,"daily":229,"monthly":230,"yearly":231},99.05,3012.78,36153.4,{"name":233,"vram_gb":226,"cheapest_hour":10,"cost":10,"provider":10,"estimated_tps":234},"B200 SXM",345.7,{"posts_count":40,"benchmarks_count":40}]