[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-deepseek-r1-distill-llama-70b":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":29,"variants":30,"quantizations":31,"requirements":58,"gpu_recommendations":143,"fitting_gpus":215,"community":243},5,"deepseek-r1-distill-llama-70b","DeepSeek R1 Distill Llama 70B","deepseek-ai\u002FDeepSeek-R1-Distill-Llama-70B","deepseek-ai","transformer",null,70600000000,"70.6B",131072,"MIT",1100000,3800,"published","70B distilled reasoning model, requires 2x48GB or 80GB datacenter GPUs.","https:\u002F\u002Fhuggingface.co\u002Fdeepseek-ai\u002FDeepSeek-R1-Distill-Llama-70B","2026-08-12T02:22:23+00:00",{"title":6,"description":18,"image":10,"robots":22,"canonical_url":10},"index, follow",{"name":24,"slug":25},"LLM","llm",{"name":27,"slug":28},"DeepSeek","deepseek",0.1341,[],[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":115,"GGUF":129},{"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",4096,131.5,171.3,256.95,244.14,"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",16384,64,299.07,448.61,309.14,{"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",8192,2,194.61,291.92,270.14,{"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},65.75,88.13,132.19,141.57,{"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},208.34,312.51,206.57,{"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},107.66,161.48,167.57,{"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":107,"recommended":111},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":103,"kv_cache_gb":45,"vram_gb":104,"ram_gb":105,"disk_gb":106,"requirement_source":67,"confidence":68},34.11,48.1,72.15,92.21,{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":103,"kv_cache_gb":72,"vram_gb":108,"ram_gb":109,"disk_gb":110,"requirement_source":67,"confidence":68},164.67,247,157.21,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":103,"kv_cache_gb":44,"vram_gb":112,"ram_gb":113,"disk_gb":114,"requirement_source":67,"confidence":68},65.81,98.71,118.21,{"minimum":116,"production":121,"recommended":125},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":117,"kv_cache_gb":45,"vram_gb":118,"ram_gb":119,"disk_gb":120,"requirement_source":67,"confidence":68},34.52,48.62,72.93,92.85,{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":117,"kv_cache_gb":72,"vram_gb":122,"ram_gb":123,"disk_gb":124,"requirement_source":67,"confidence":68},165.24,247.86,157.85,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":117,"kv_cache_gb":44,"vram_gb":126,"ram_gb":127,"disk_gb":128,"requirement_source":67,"confidence":68},66.35,99.53,118.85,{"minimum":130,"production":135,"recommended":139},{"scenario":61,"context_length":62,"batch_size":40,"weight_gb":131,"kv_cache_gb":45,"vram_gb":132,"ram_gb":133,"disk_gb":134,"requirement_source":67,"confidence":68},35.34,49.66,74.49,94.13,{"scenario":70,"context_length":71,"batch_size":34,"weight_gb":131,"kv_cache_gb":72,"vram_gb":136,"ram_gb":137,"disk_gb":138,"requirement_source":67,"confidence":68},166.37,249.56,159.13,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":131,"kv_cache_gb":44,"vram_gb":140,"ram_gb":141,"disk_gb":142,"requirement_source":67,"confidence":68},67.44,101.16,120.13,{"recommended":144,"cheapest":163,"performance":176,"min_complexity":185,"cluster_options":201,"no_match":212,"required_vram_gb":112,"candidate_count":213,"usage":214},{"gpu_model":145,"gpu_model_id":146,"gpu_count":40,"total_vram_gb":147,"hour_price":148,"monthly_cost":149,"providers":150,"bandwidth_gbps":152,"fp16_tflops":153,"interconnect_score":154,"parallel_efficiency":40,"score":155,"tier":156,"perf_metric":157,"perf_label":158,"perf_value":159,"workload":10,"cost_metric":160},"H200 SXM",11,141,3.5,2555,[151],"lambda",4800,989,40,0.5955,"balanced","tok\u002Fs","140.7 tok\u002Fs",140.7,{"effective_value":161,"effective_unit":157,"capacity_factor":162},98.5,0.7,{"gpu_model":164,"gpu_model_id":165,"gpu_count":44,"total_vram_gb":166,"hour_price":167,"monthly_cost":168,"providers":169,"bandwidth_gbps":41,"fp16_tflops":41,"interconnect_score":154,"parallel_efficiency":171,"score":172,"tier":173,"perf_metric":157,"perf_label":174,"perf_value":41,"workload":10,"cost_metric":175},"Tesla V100",17,128,0.0272,158.85,[170],"vast",0.4,0.4938,"cheapest","0 tok\u002Fs",{"effective_value":41,"effective_unit":157,"capacity_factor":162},{"gpu_model":145,"gpu_model_id":146,"gpu_count":44,"total_vram_gb":177,"hour_price":148,"monthly_cost":178,"providers":179,"bandwidth_gbps":152,"fp16_tflops":153,"interconnect_score":154,"parallel_efficiency":171,"score":180,"tier":156,"perf_metric":157,"perf_label":181,"perf_value":182,"workload":10,"cost_metric":183},1128,20440,[151],0.2197,"450.3 tok\u002Fs",450.3,{"effective_value":184,"effective_unit":157,"capacity_factor":162},315.2,{"gpu_model":186,"gpu_model_id":187,"gpu_count":40,"total_vram_gb":188,"hour_price":189,"monthly_cost":190,"providers":191,"bandwidth_gbps":194,"fp16_tflops":195,"interconnect_score":154,"parallel_efficiency":40,"score":196,"tier":156,"perf_metric":157,"perf_label":197,"perf_value":198,"workload":10,"cost_metric":199},"A100 80GB",9,80,1.2,876,[170,192,193,151],"tensordock","runpod",2039,77.97,0.6669,"59.8 tok\u002Fs",59.8,{"effective_value":200,"effective_unit":157,"capacity_factor":162},41.9,[202],{"gpu_model":203,"gpu_model_id":204,"gpu_count":44,"total_vram_gb":72,"hour_price":205,"monthly_cost":206,"providers":207,"bandwidth_gbps":208,"fp16_tflops":204,"interconnect_score":154,"parallel_efficiency":171,"insufficient":209,"vram_shortfall_gb":210,"score":211,"tier":156},"RTX 5060 Ti",24,0.0554,323.54,[170],448,true,1.81,0.5102,false,19,"value",[216,220,228,232,240],{"name":186,"vram_gb":188,"cheapest_hour":189,"cost":217,"provider":170,"estimated_tps":198},{"hourly":189,"daily":218,"monthly":190,"yearly":219},28.8,10512,{"name":221,"vram_gb":188,"cheapest_hour":222,"cost":223,"provider":170,"estimated_tps":227},"H100 SXM",1.6022,{"hourly":222,"daily":224,"monthly":225,"yearly":226},38.45,1169.61,14035.27,98.2,{"name":145,"vram_gb":147,"cheapest_hour":148,"cost":229,"provider":151,"estimated_tps":159},{"hourly":148,"daily":230,"monthly":149,"yearly":231},84,30660,{"name":233,"vram_gb":234,"cheapest_hour":235,"cost":236,"provider":170,"estimated_tps":41},"B200",180,4.1271,{"hourly":235,"daily":237,"monthly":238,"yearly":239},99.05,3012.78,36153.4,{"name":241,"vram_gb":234,"cheapest_hour":10,"cost":10,"provider":10,"estimated_tps":242},"B200 SXM",228.7,{"posts_count":41,"benchmarks_count":41}]