[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-ornith-1-5-9b-gguf":3},{"id":4,"slug":5,"name":6,"hf_id":6,"organization":7,"architecture":8,"architecture_config":8,"parameters":9,"parameters_label":10,"context_length":8,"license":8,"downloads":11,"likes":12,"status":13,"description":8,"huggingface_url":14,"created_at":15,"seo":16,"category":19,"family":22,"score":24,"variants":25,"quantizations":26,"requirements":53,"gpu_recommendations":135,"fitting_gpus":201,"community":236},529,"ornith-1-5-9b-gguf","ornith-ai\u002FOrnith-1.5-9B-GGUF","ornith-ai",null,9000000000,"9B",5177548,521,"published","https:\u002F\u002Fhuggingface.co\u002Fornith-ai\u002FOrnith-1.5-9B-GGUF","2026-09-11T12:13:04+00:00",{"title":6,"description":17,"image":8,"robots":18,"canonical_url":8},"AI model deployment & compute intelligence — compare AI models, GPU requirements, benchmarks, cloud GPU rental pricing and deployment cost analysis for DeepSeek, Qwen, Llama, Wan and more.","index, follow",{"name":20,"slug":21},"LLM","llm",{"name":23,"slug":7},"Ornith-ai",0.0155,[],[27,32,37,42,46,50],{"format":28,"bits":29,"size_factor":30,"quality_loss":31},"AWQ",4,0.263,0.03,{"format":33,"bits":34,"size_factor":35,"quality_loss":36},"FP16",16,1,0,{"format":38,"bits":39,"size_factor":40,"quality_loss":41},"FP8",8,0.5,0.01,{"format":43,"bits":29,"size_factor":44,"quality_loss":45},"GGUF",0.25,0.05,{"format":47,"bits":29,"size_factor":48,"quality_loss":49},"GPTQ",0.275,0.04,{"format":51,"bits":39,"size_factor":40,"quality_loss":52},"INT8",0.02,{"FP16":54,"FP8":78,"INT8":92,"AWQ":96,"GPTQ":109,"GGUF":122},{"minimum":55,"production":64,"recommended":71},{"scenario":56,"context_length":57,"batch_size":35,"weight_gb":58,"kv_cache_gb":40,"vram_gb":59,"ram_gb":60,"disk_gb":61,"requirement_source":62,"confidence":63},"minimum",4096,16.76,26.16,39.23,65.15,"inferred",0.95,{"scenario":65,"context_length":66,"batch_size":29,"weight_gb":58,"kv_cache_gb":67,"vram_gb":68,"ram_gb":69,"disk_gb":70,"requirement_source":62,"confidence":63},"production",16384,64,140.73,211.1,130.15,{"scenario":72,"context_length":73,"batch_size":74,"weight_gb":58,"kv_cache_gb":39,"vram_gb":75,"ram_gb":76,"disk_gb":77,"requirement_source":62,"confidence":63},"recommended",8192,2,42.87,64.31,91.15,{"minimum":79,"production":84,"recommended":88},{"scenario":56,"context_length":57,"batch_size":35,"weight_gb":80,"kv_cache_gb":40,"vram_gb":81,"ram_gb":82,"disk_gb":83,"requirement_source":62,"confidence":63},8.38,15.55,32,52.08,{"scenario":65,"context_length":66,"batch_size":29,"weight_gb":80,"kv_cache_gb":67,"vram_gb":85,"ram_gb":86,"disk_gb":87,"requirement_source":62,"confidence":63},129.17,193.75,117.08,{"scenario":72,"context_length":73,"batch_size":74,"weight_gb":80,"kv_cache_gb":39,"vram_gb":89,"ram_gb":90,"disk_gb":91,"requirement_source":62,"confidence":63},31.79,47.68,78.08,{"minimum":93,"production":94,"recommended":95},{"scenario":56,"context_length":57,"batch_size":35,"weight_gb":80,"kv_cache_gb":40,"vram_gb":81,"ram_gb":82,"disk_gb":83,"requirement_source":62,"confidence":63},{"scenario":65,"context_length":66,"batch_size":29,"weight_gb":80,"kv_cache_gb":67,"vram_gb":85,"ram_gb":86,"disk_gb":87,"requirement_source":62,"confidence":63},{"scenario":72,"context_length":73,"batch_size":74,"weight_gb":80,"kv_cache_gb":39,"vram_gb":89,"ram_gb":90,"disk_gb":91,"requirement_source":62,"confidence":63},{"minimum":97,"production":101,"recommended":105},{"scenario":56,"context_length":57,"batch_size":35,"weight_gb":98,"kv_cache_gb":40,"vram_gb":99,"ram_gb":82,"disk_gb":100,"requirement_source":62,"confidence":63},4.35,10.45,45.78,{"scenario":65,"context_length":66,"batch_size":29,"weight_gb":98,"kv_cache_gb":67,"vram_gb":102,"ram_gb":103,"disk_gb":104,"requirement_source":62,"confidence":63},123.6,185.4,110.78,{"scenario":72,"context_length":73,"batch_size":74,"weight_gb":98,"kv_cache_gb":39,"vram_gb":106,"ram_gb":107,"disk_gb":108,"requirement_source":62,"confidence":63},26.45,39.68,71.78,{"minimum":110,"production":114,"recommended":118},{"scenario":56,"context_length":57,"batch_size":35,"weight_gb":111,"kv_cache_gb":40,"vram_gb":112,"ram_gb":82,"disk_gb":113,"requirement_source":62,"confidence":63},4.4,10.52,45.86,{"scenario":65,"context_length":66,"batch_size":29,"weight_gb":111,"kv_cache_gb":67,"vram_gb":115,"ram_gb":116,"disk_gb":117,"requirement_source":62,"confidence":63},123.67,185.51,110.86,{"scenario":72,"context_length":73,"batch_size":74,"weight_gb":111,"kv_cache_gb":39,"vram_gb":119,"ram_gb":120,"disk_gb":121,"requirement_source":62,"confidence":63},26.52,39.78,71.86,{"minimum":123,"production":127,"recommended":131},{"scenario":56,"context_length":57,"batch_size":35,"weight_gb":124,"kv_cache_gb":40,"vram_gb":125,"ram_gb":82,"disk_gb":126,"requirement_source":62,"confidence":63},4.51,10.65,46.03,{"scenario":65,"context_length":66,"batch_size":29,"weight_gb":124,"kv_cache_gb":67,"vram_gb":128,"ram_gb":129,"disk_gb":130,"requirement_source":62,"confidence":63},123.82,185.73,111.03,{"scenario":72,"context_length":73,"batch_size":74,"weight_gb":124,"kv_cache_gb":39,"vram_gb":132,"ram_gb":133,"disk_gb":134,"requirement_source":62,"confidence":63},26.66,39.99,72.03,{"recommended":136,"cheapest":158,"performance":169,"min_complexity":184,"cluster_options":197,"no_match":198,"required_vram_gb":106,"candidate_count":199,"usage":200},{"gpu_model":137,"gpu_model_id":138,"gpu_count":35,"total_vram_gb":139,"hour_price":140,"monthly_cost":141,"providers":142,"bandwidth_gbps":147,"fp16_tflops":148,"interconnect_score":149,"parallel_efficiency":35,"score":150,"tier":151,"perf_metric":152,"perf_label":153,"perf_value":154,"workload":8,"cost_metric":155},"H100 SXM",10,80,1.7341,1265.89,[143,144,145,146],"vast","tensordock","lambda","runpod",3350,66.9,40,0.5757,"balanced","tok\u002Fs","770.1 tok\u002Fs",770.1,{"effective_value":156,"effective_unit":152,"capacity_factor":157},539.1,0.7,{"gpu_model":159,"gpu_model_id":160,"gpu_count":74,"total_vram_gb":82,"hour_price":161,"monthly_cost":162,"providers":163,"bandwidth_gbps":36,"fp16_tflops":36,"interconnect_score":149,"parallel_efficiency":164,"score":165,"tier":166,"perf_metric":152,"perf_label":167,"perf_value":36,"workload":8,"cost_metric":168},"Tesla V100",17,0.0489,71.39,[143],0.8,0.6256,"cheapest","0 tok\u002Fs",{"effective_value":36,"effective_unit":152,"capacity_factor":157},{"gpu_model":170,"gpu_model_id":171,"gpu_count":39,"total_vram_gb":172,"hour_price":173,"monthly_cost":174,"providers":175,"bandwidth_gbps":176,"fp16_tflops":177,"interconnect_score":149,"parallel_efficiency":178,"score":179,"tier":151,"perf_metric":152,"perf_label":180,"perf_value":181,"workload":8,"cost_metric":182},"H200 SXM",11,1128,3.5,20440,[145],4800,989,0.4,0.2197,"3531 tok\u002Fs",3531,{"effective_value":183,"effective_unit":152,"capacity_factor":157},2471.7,{"gpu_model":185,"gpu_model_id":186,"gpu_count":35,"total_vram_gb":187,"hour_price":188,"monthly_cost":189,"providers":190,"bandwidth_gbps":191,"fp16_tflops":192,"interconnect_score":149,"parallel_efficiency":35,"score":193,"tier":166,"perf_metric":152,"perf_label":194,"perf_value":195,"workload":8,"cost_metric":196},"RTX A6000",6,48,0.3622,264.41,[143,145],768,77,0.6369,"176.6 tok\u002Fs",176.6,{"effective_value":102,"effective_unit":152,"capacity_factor":157},[],false,26,"value",[202,206,213,221,229],{"name":185,"vram_gb":187,"cheapest_hour":188,"cost":203,"provider":143,"estimated_tps":195},{"hourly":188,"daily":204,"monthly":189,"yearly":205},8.69,3172.87,{"name":207,"vram_gb":139,"cheapest_hour":208,"cost":209,"provider":143,"estimated_tps":36},"A100 SXM4",0.3781,{"hourly":208,"daily":210,"monthly":211,"yearly":212},9.07,276.01,3312.16,{"name":214,"vram_gb":82,"cheapest_hour":215,"cost":216,"provider":143,"estimated_tps":220},"RTX 5090",0.4006,{"hourly":215,"daily":217,"monthly":218,"yearly":219},9.61,292.44,3509.26,412,{"name":222,"vram_gb":187,"cheapest_hour":223,"cost":224,"provider":143,"estimated_tps":228},"L40S",0.4415,{"hourly":223,"daily":225,"monthly":226,"yearly":227},10.6,322.3,3867.54,198.6,{"name":230,"vram_gb":139,"cheapest_hour":231,"cost":232,"provider":143,"estimated_tps":36},"A100 PCIE",0.4849,{"hourly":231,"daily":233,"monthly":234,"yearly":235},11.64,353.98,4247.72,{"posts_count":36,"benchmarks_count":36}]