[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-deepseek-r1-distill-qwen-14b":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":57,"gpu_recommendations":140,"fitting_gpus":207,"community":242},4,"deepseek-r1-distill-qwen-14b","DeepSeek R1 Distill Qwen 14B","deepseek-ai\u002FDeepSeek-R1-Distill-Qwen-14B","deepseek-ai","transformer",null,14700000000,"14.7B",131072,"MIT",1600000,4200,"published","14B distilled reasoning model, fits comfortably on 16-24GB GPUs.","https:\u002F\u002Fhuggingface.co\u002Fdeepseek-ai\u002FDeepSeek-R1-Distill-Qwen-14B","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},"Qwen","qwen",0.0489,[],[32,36,41,46,50,54],{"format":33,"bits":4,"size_factor":34,"quality_loss":35},"AWQ",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":4,"size_factor":48,"quality_loss":49},"GGUF",0.25,0.05,{"format":51,"bits":4,"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":127},{"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",4096,27.38,39.59,59.38,81.71,"estimated",0.95,{"scenario":69,"context_length":70,"batch_size":4,"weight_gb":62,"kv_cache_gb":71,"vram_gb":72,"ram_gb":73,"disk_gb":74,"requirement_source":66,"confidence":67},"production",16384,64,155.39,233.08,146.71,{"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",8192,2,56.91,85.37,107.71,{"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},13.69,22.27,33.4,60.36,{"scenario":69,"context_length":70,"batch_size":4,"weight_gb":84,"kv_cache_gb":71,"vram_gb":89,"ram_gb":90,"disk_gb":91,"requirement_source":66,"confidence":67},136.49,204.74,125.36,{"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},38.81,58.21,86.36,{"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":4,"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},7.1,13.93,32,50.08,{"scenario":69,"context_length":70,"batch_size":4,"weight_gb":102,"kv_cache_gb":71,"vram_gb":107,"ram_gb":108,"disk_gb":109,"requirement_source":66,"confidence":67},127.4,191.1,115.08,{"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},30.09,45.14,76.08,{"minimum":115,"production":119,"recommended":123},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":116,"kv_cache_gb":44,"vram_gb":117,"ram_gb":104,"disk_gb":118,"requirement_source":66,"confidence":67},7.19,14.04,50.21,{"scenario":69,"context_length":70,"batch_size":4,"weight_gb":116,"kv_cache_gb":71,"vram_gb":120,"ram_gb":121,"disk_gb":122,"requirement_source":66,"confidence":67},127.52,191.28,115.21,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":116,"kv_cache_gb":43,"vram_gb":124,"ram_gb":125,"disk_gb":126,"requirement_source":66,"confidence":67},30.21,45.31,76.21,{"minimum":128,"production":132,"recommended":136},{"scenario":60,"context_length":61,"batch_size":39,"weight_gb":129,"kv_cache_gb":44,"vram_gb":130,"ram_gb":104,"disk_gb":131,"requirement_source":66,"confidence":67},7.36,14.26,50.48,{"scenario":69,"context_length":70,"batch_size":4,"weight_gb":129,"kv_cache_gb":71,"vram_gb":133,"ram_gb":134,"disk_gb":135,"requirement_source":66,"confidence":67},127.75,191.63,115.48,{"scenario":76,"context_length":77,"batch_size":78,"weight_gb":129,"kv_cache_gb":43,"vram_gb":137,"ram_gb":138,"disk_gb":139,"requirement_source":66,"confidence":67},30.43,45.65,76.48,{"recommended":141,"cheapest":163,"performance":174,"min_complexity":189,"cluster_options":203,"no_match":204,"required_vram_gb":111,"candidate_count":205,"usage":206},{"gpu_model":142,"gpu_model_id":143,"gpu_count":39,"total_vram_gb":144,"hour_price":145,"monthly_cost":146,"providers":147,"bandwidth_gbps":152,"fp16_tflops":153,"interconnect_score":154,"parallel_efficiency":39,"score":155,"tier":156,"perf_metric":157,"perf_label":158,"perf_value":159,"workload":10,"cost_metric":160},"H100 SXM",10,80,1.6022,1169.61,[148,149,150,151],"vast","tensordock","lambda","runpod",3350,66.9,40,0.5899,"balanced","tok\u002Fs","471.8 tok\u002Fs",471.8,{"effective_value":161,"effective_unit":157,"capacity_factor":162},330.3,0.7,{"gpu_model":164,"gpu_model_id":165,"gpu_count":78,"total_vram_gb":104,"hour_price":166,"monthly_cost":167,"providers":168,"bandwidth_gbps":40,"fp16_tflops":40,"interconnect_score":154,"parallel_efficiency":169,"score":170,"tier":171,"perf_metric":157,"perf_label":172,"perf_value":40,"workload":10,"cost_metric":173},"Tesla V100",17,0.0272,39.71,[148],0.8,0.5959,"cheapest","0 tok\u002Fs",{"effective_value":40,"effective_unit":157,"capacity_factor":162},{"gpu_model":175,"gpu_model_id":176,"gpu_count":43,"total_vram_gb":177,"hour_price":178,"monthly_cost":179,"providers":180,"bandwidth_gbps":181,"fp16_tflops":182,"interconnect_score":154,"parallel_efficiency":183,"score":184,"tier":156,"perf_metric":157,"perf_label":185,"perf_value":186,"workload":10,"cost_metric":187},"H200 SXM",11,1128,3.5,20440,[150],4800,989,0.4,0.2197,"2163.4 tok\u002Fs",2163.4,{"effective_value":188,"effective_unit":157,"capacity_factor":162},1514.4,{"gpu_model":190,"gpu_model_id":191,"gpu_count":39,"total_vram_gb":192,"hour_price":193,"monthly_cost":194,"providers":195,"bandwidth_gbps":196,"fp16_tflops":197,"interconnect_score":154,"parallel_efficiency":39,"score":198,"tier":171,"perf_metric":157,"perf_label":199,"perf_value":200,"workload":10,"cost_metric":201},"RTX A6000",6,48,0.3001,219.07,[148,150],768,77,0.6581,"108.2 tok\u002Fs",108.2,{"effective_value":202,"effective_unit":157,"capacity_factor":162},75.7,[],false,24,"value",[208,212,220,228,235],{"name":190,"vram_gb":192,"cheapest_hour":193,"cost":209,"provider":148,"estimated_tps":200},{"hourly":193,"daily":210,"monthly":194,"yearly":211},7.2,2628.88,{"name":213,"vram_gb":104,"cheapest_hour":214,"cost":215,"provider":148,"estimated_tps":219},"RTX 5090",0.3222,{"hourly":214,"daily":216,"monthly":217,"yearly":218},7.73,235.21,2822.47,252.4,{"name":221,"vram_gb":192,"cheapest_hour":222,"cost":223,"provider":148,"estimated_tps":227},"L40S",0.4669,{"hourly":222,"daily":224,"monthly":225,"yearly":226},11.21,340.84,4090.04,121.7,{"name":229,"vram_gb":192,"cheapest_hour":230,"cost":231,"provider":148,"estimated_tps":40},"RTX PRO 6000 WS",0.8022,{"hourly":230,"daily":232,"monthly":233,"yearly":234},19.25,585.61,7027.27,{"name":236,"vram_gb":192,"cheapest_hour":237,"cost":238,"provider":148,"estimated_tps":40},"RTX PRO 6000 S",1.0131,{"hourly":237,"daily":239,"monthly":240,"yearly":241},24.31,739.56,8874.76,{"posts_count":40,"benchmarks_count":40}]