{ "protocolVersion": "osai-bench/1.3", "clientVersion": "0.10.0", "scoringVersion": "osai-bench-derive/1.3", "createdAt": "2026-08-03T05:14:27.645Z", "qualityOverride": false, "cohortEligible": true, "qualityConditions": [], "runtime": { "name": "ollama", "version": "0.32.5", "endpoint": "loopback", "layerAssignment": null, "offloadPlacement": { "source": "ollama.ps.size_vram", "granularity": "bytes", "residentBytes": 20691549392, "vramResidentBytes": 8704470547, "hostResidentBytes": 11987078845, "vramResidentFraction": 0.42067756174728127 }, "kvCacheMetadata": { "source": "ollama.show.model_info", "architecture": "laguna", "blockCount": 40, "kvHeadCount": 8, "attentionHeadCount": null, "embeddingLength": 2048, "headDimension": 128, "resolvedElementType": null, "projectedBytes": null, "calculationAvailable": false, "missingInputs": [ "resolvedKvCacheElementType" ] }, "environment": { "source": "client-process-env", "authoritative": false, "note": "Read from the benchmark client's own process environment. The Ollama server may have been started with a different environment; Ollama exposes no endpoint reporting its resolved configuration.", "declared": { "OLLAMA_KV_CACHE_TYPE": null, "OLLAMA_FLASH_ATTENTION": null, "OLLAMA_CONTEXT_LENGTH": null, "OLLAMA_NUM_PARALLEL": null, "OLLAMA_GPU_OVERHEAD": null, "OLLAMA_SCHED_SPREAD": null, "OLLAMA_LLM_LIBRARY": null, "LLAMA_ARG_FIT": null, "LLAMA_ARG_FIT_TARGET": null, "OLLAMA_MAX_LOADED_MODELS": null, "OLLAMA_KEEP_ALIVE": null, "OLLAMA_DEBUG": null, "OLLAMA_MODELS": false, "OLLAMA_HOST": false }, "declaredNonDefault": [] } }, "model": { "identifier": "laguna-xs-2.1:latest", "digest": "0175be1e57f44bb4a96779d1840dbadd84399ab87bf70688c321ecadeadd757f", "family": "laguna", "parameterSize": "33.4B", "quantization": "Q4_K_M", "weightsBytes": 20274303147, "weightsSource": "ollama.tags.size" }, "system": { "cpu": { "model": "12th Gen Intel(R) Core(TM) i9-12900K" }, "gpu": { "present": true, "model": "NVIDIA GeForce RTX 3080", "totalVramBytes": 10737418240, "freeVramBytesAtCheck": 10326376448, "freeVramBytesAtLoad": 1070596096, "utilizationPercentAtCheck": 0, "driverVersion": "595.71.05", "provider": "nvidia-smi" }, "memory": { "totalBytes": 32817025024 }, "os": { "platform": "linux", "version": "Ubuntu 26.04 LTS", "architecture": "x64" }, "power": { "present": false, "onBattery": false } }, "configuration": { "memoryBandwidthGBps": 760, "memoryBandwidthSource": "manufacturer-table", "memoryBandwidthTableVersion": "osai-gpu-memory-bandwidth/2", "memoryBandwidthEntryId": "nvidia-geforce-rtx-3080-10gb", "fixedOptions": { "temperature": 0, "seed": 42, "stream": true }, "workloads": { "w1": { "numPredict": 1, "numCtx": 512, "keepAlive": "5m", "promptTokenRange": null, "warmups": 0, "repetitions": 1, "varyPromptPerCall": false }, "w2": { "numPredict": 128, "numCtx": 4096, "keepAlive": "5m", "promptTokenRange": { "min": 20, "max": 64 }, "warmups": 1, "repetitions": 5, "varyPromptPerCall": false }, "w3": { "numPredict": 1, "numCtx": 4096, "keepAlive": "5m", "promptTokenRange": { "min": 2000, "max": 4095 }, "warmups": 1, "repetitions": 5, "varyPromptPerCall": true }, "w4": { "numPredict": 512, "numCtx": 4096, "keepAlive": "5m", "promptTokenRange": { "min": 20, "max": 64 }, "warmups": 1, "repetitions": 5, "varyPromptPerCall": false } }, "resolved": { "fixedOptions": { "temperature": 0, "seed": 42, "stream": true }, "workloads": { "w1": { "numPredict": 1, "numCtx": 512, "keepAlive": "5m" }, "w2": { "numPredict": 128, "numCtx": 4096, "keepAlive": "5m" }, "w3": { "numPredict": 1, "numCtx": 4096, "keepAlive": "5m" }, "w4": { "numPredict": 512, "numCtx": 4096, "keepAlive": "5m" } }, "runtimeModelParameters": null, "unresolvedRuntimeDefaults": true } }, "rawMeasurements": { "workloads": { "w1": { "warmup": null, "measuredPasses": [ { "index": 1, "valid": true, "attempts": [ { "measurement": { "total_duration": 4326994367, "load_duration": 3657783694, "prompt_eval_count": 47, "prompt_eval_duration": 665190000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 4327.551889000002 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 4326994367, "load_duration": 3657783694, "prompt_eval_count": 47, "prompt_eval_duration": 665190000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 4327.551889000002 }, "validity": { "valid": true, "reasons": [] } } ], "failed": false }, "w2": { "warmup": { "total_duration": 8340403376, "load_duration": 4290243242, "prompt_eval_count": 81, "prompt_eval_duration": 1148379000, "eval_count": 128, "eval_duration": 2895977000, "timeToFirstTokenMs": 5446.362873999999 }, "measuredPasses": [ { "index": 1, "valid": false, "attempts": [ { "measurement": { "total_duration": 3171684207, "load_duration": 131020332, "prompt_eval_count": 81, "prompt_eval_duration": 87036000, "eval_count": 128, "eval_duration": 2934159000, "timeToFirstTokenMs": 238.27468000000226 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3200671183, "load_duration": 135815043, "prompt_eval_count": 81, "prompt_eval_duration": 86398000, "eval_count": 128, "eval_duration": 2943851000, "timeToFirstTokenMs": 257.2710999999981 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3116646571, "load_duration": 89951348, "prompt_eval_count": 81, "prompt_eval_duration": 88468000, "eval_count": 128, "eval_duration": 2936039000, "timeToFirstTokenMs": 181.1256910000011 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 3116646571, "load_duration": 89951348, "prompt_eval_count": 81, "prompt_eval_duration": 88468000, "eval_count": 128, "eval_duration": 2936039000, "timeToFirstTokenMs": 181.1256910000011 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 2, "valid": false, "attempts": [ { "measurement": { "total_duration": 3167658868, "load_duration": 130511198, "prompt_eval_count": 81, "prompt_eval_duration": 91178000, "eval_count": 128, "eval_duration": 2943164000, "timeToFirstTokenMs": 224.87047000000166 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3151570412, "load_duration": 128800884, "prompt_eval_count": 81, "prompt_eval_duration": 99067000, "eval_count": 128, "eval_duration": 2921093000, "timeToFirstTokenMs": 230.96387400000094 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3113832247, "load_duration": 99354660, "prompt_eval_count": 81, "prompt_eval_duration": 87960000, "eval_count": 128, "eval_duration": 2924291000, "timeToFirstTokenMs": 189.99806900000112 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 3113832247, "load_duration": 99354660, "prompt_eval_count": 81, "prompt_eval_duration": 87960000, "eval_count": 128, "eval_duration": 2924291000, "timeToFirstTokenMs": 189.99806900000112 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 3, "valid": false, "attempts": [ { "measurement": { "total_duration": 3119185684, "load_duration": 103282407, "prompt_eval_count": 81, "prompt_eval_duration": 91982000, "eval_count": 128, "eval_duration": 2921678000, "timeToFirstTokenMs": 197.98433099999966 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3157217426, "load_duration": 137735661, "prompt_eval_count": 81, "prompt_eval_duration": 96396000, "eval_count": 128, "eval_duration": 2920201000, "timeToFirstTokenMs": 237.3712400000004 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3103045240, "load_duration": 97292638, "prompt_eval_count": 81, "prompt_eval_duration": 88595000, "eval_count": 128, "eval_duration": 2914934000, "timeToFirstTokenMs": 188.5797390000007 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 3103045240, "load_duration": 97292638, "prompt_eval_count": 81, "prompt_eval_duration": 88595000, "eval_count": 128, "eval_duration": 2914934000, "timeToFirstTokenMs": 188.5797390000007 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 4, "valid": false, "attempts": [ { "measurement": { "total_duration": 3138576763, "load_duration": 115268330, "prompt_eval_count": 81, "prompt_eval_duration": 88933000, "eval_count": 128, "eval_duration": 2932333000, "timeToFirstTokenMs": 206.5510990000039 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3140801924, "load_duration": 122411661, "prompt_eval_count": 81, "prompt_eval_duration": 90546000, "eval_count": 128, "eval_duration": 2924878000, "timeToFirstTokenMs": 216.48934400000144 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3124843229, "load_duration": 111483779, "prompt_eval_count": 81, "prompt_eval_duration": 93868000, "eval_count": 128, "eval_duration": 2916981000, "timeToFirstTokenMs": 208.17968099999416 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 3124843229, "load_duration": 111483779, "prompt_eval_count": 81, "prompt_eval_duration": 93868000, "eval_count": 128, "eval_duration": 2916981000, "timeToFirstTokenMs": 208.17968099999416 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 5, "valid": false, "attempts": [ { "measurement": { "total_duration": 3143143634, "load_duration": 122332235, "prompt_eval_count": 81, "prompt_eval_duration": 87419000, "eval_count": 128, "eval_duration": 2931091000, "timeToFirstTokenMs": 212.794120999999 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3174025044, "load_duration": 133637101, "prompt_eval_count": 81, "prompt_eval_duration": 88170000, "eval_count": 128, "eval_duration": 2950049000, "timeToFirstTokenMs": 224.5858959999896 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 3126250184, "load_duration": 112853671, "prompt_eval_count": 81, "prompt_eval_duration": 87929000, "eval_count": 128, "eval_duration": 2923185000, "timeToFirstTokenMs": 203.61346700000286 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 3126250184, "load_duration": 112853671, "prompt_eval_count": 81, "prompt_eval_duration": 87929000, "eval_count": 128, "eval_duration": 2923185000, "timeToFirstTokenMs": 203.61346700000286 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "failed": true }, "w3": { "warmup": { "total_duration": 7560524437, "load_duration": 123577794, "prompt_eval_count": 2706, "prompt_eval_duration": 7418836000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7560.77967399999 }, "measuredPasses": [ { "index": 1, "valid": true, "attempts": [ { "measurement": { "total_duration": 7683826495, "load_duration": 82799857, "prompt_eval_count": 2706, "prompt_eval_duration": 7461974000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7684.165706 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 7683826495, "load_duration": 82799857, "prompt_eval_count": 2706, "prompt_eval_duration": 7461974000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7684.165706 }, "validity": { "valid": true, "reasons": [] } }, { "index": 2, "valid": true, "attempts": [ { "measurement": { "total_duration": 7661573257, "load_duration": 108361433, "prompt_eval_count": 2706, "prompt_eval_duration": 7425399000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7661.87535100001 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 7661573257, "load_duration": 108361433, "prompt_eval_count": 2706, "prompt_eval_duration": 7425399000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7661.87535100001 }, "validity": { "valid": true, "reasons": [] } }, { "index": 3, "valid": true, "attempts": [ { "measurement": { "total_duration": 7715174660, "load_duration": 109148990, "prompt_eval_count": 2706, "prompt_eval_duration": 7447501000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7715.626197000005 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 7715174660, "load_duration": 109148990, "prompt_eval_count": 2706, "prompt_eval_duration": 7447501000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7715.626197000005 }, "validity": { "valid": true, "reasons": [] } }, { "index": 4, "valid": true, "attempts": [ { "measurement": { "total_duration": 7709894648, "load_duration": 103189295, "prompt_eval_count": 2706, "prompt_eval_duration": 7448778000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7710.358832999991 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 7709894648, "load_duration": 103189295, "prompt_eval_count": 2706, "prompt_eval_duration": 7448778000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7710.358832999991 }, "validity": { "valid": true, "reasons": [] } }, { "index": 5, "valid": true, "attempts": [ { "measurement": { "total_duration": 7688588467, "load_duration": 121320919, "prompt_eval_count": 2706, "prompt_eval_duration": 7408712000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7689.0008649999945 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 7688588467, "load_duration": 121320919, "prompt_eval_count": 2706, "prompt_eval_duration": 7408712000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 7689.0008649999945 }, "validity": { "valid": true, "reasons": [] } } ], "failed": false }, "w4": { "warmup": { "total_duration": 12062248445, "load_duration": 117024216, "prompt_eval_count": 81, "prompt_eval_duration": 85704000, "eval_count": 512, "eval_duration": 11738780000, "timeToFirstTokenMs": 323.7907800000103 }, "measuredPasses": [ { "index": 1, "valid": false, "attempts": [ { "measurement": { "total_duration": 12113083092, "load_duration": 116864159, "prompt_eval_count": 81, "prompt_eval_duration": 85719000, "eval_count": 512, "eval_duration": 11852350000, "timeToFirstTokenMs": 261.19939299998805 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 12020599613, "load_duration": 130323238, "prompt_eval_count": 81, "prompt_eval_duration": 86802000, "eval_count": 512, "eval_duration": 11801668000, "timeToFirstTokenMs": 219.475317000004 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 12039492387, "load_duration": 92166668, "prompt_eval_count": 81, "prompt_eval_duration": 87393000, "eval_count": 512, "eval_duration": 11858154000, "timeToFirstTokenMs": 181.70905299999868 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 12039492387, "load_duration": 92166668, "prompt_eval_count": 81, "prompt_eval_duration": 87393000, "eval_count": 512, "eval_duration": 11858154000, "timeToFirstTokenMs": 181.70905299999868 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 2, "valid": false, "attempts": [ { "measurement": { "total_duration": 12005062560, "load_duration": 95591569, "prompt_eval_count": 81, "prompt_eval_duration": 91116000, "eval_count": 512, "eval_duration": 11816467000, "timeToFirstTokenMs": 188.9718920000014 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 12052834725, "load_duration": 131183861, "prompt_eval_count": 81, "prompt_eval_duration": 88931000, "eval_count": 512, "eval_duration": 11830546000, "timeToFirstTokenMs": 222.64303199999267 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 12028334707, "load_duration": 102847988, "prompt_eval_count": 81, "prompt_eval_duration": 87087000, "eval_count": 512, "eval_duration": 11836458000, "timeToFirstTokenMs": 192.32092999998713 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 12028334707, "load_duration": 102847988, "prompt_eval_count": 81, "prompt_eval_duration": 87087000, "eval_count": 512, "eval_duration": 11836458000, "timeToFirstTokenMs": 192.32092999998713 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 3, "valid": false, "attempts": [ { "measurement": { "total_duration": 12056252919, "load_duration": 93941957, "prompt_eval_count": 81, "prompt_eval_duration": 89102000, "eval_count": 512, "eval_duration": 11871296000, "timeToFirstTokenMs": 185.25537199998507 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 12012738222, "load_duration": 90687926, "prompt_eval_count": 81, "prompt_eval_duration": 84725000, "eval_count": 512, "eval_duration": 11835238000, "timeToFirstTokenMs": 177.8300290000043 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 12019929485, "load_duration": 117376254, "prompt_eval_count": 81, "prompt_eval_duration": 85560000, "eval_count": 512, "eval_duration": 11814967000, "timeToFirstTokenMs": 205.52674800000386 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 12019929485, "load_duration": 117376254, "prompt_eval_count": 81, "prompt_eval_duration": 85560000, "eval_count": 512, "eval_duration": 11814967000, "timeToFirstTokenMs": 205.52674800000386 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 4, "valid": false, "attempts": [ { "measurement": { "total_duration": 12017911782, "load_duration": 106125756, "prompt_eval_count": 81, "prompt_eval_duration": 89983000, "eval_count": 512, "eval_duration": 11818971000, "timeToFirstTokenMs": 199.4642739999981 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 12057567899, "load_duration": 120323708, "prompt_eval_count": 81, "prompt_eval_duration": 85504000, "eval_count": 512, "eval_duration": 11849967000, "timeToFirstTokenMs": 207.90987999999197 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 11985071152, "load_duration": 98800094, "prompt_eval_count": 81, "prompt_eval_duration": 86284000, "eval_count": 512, "eval_duration": 11797629000, "timeToFirstTokenMs": 187.8317490000045 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 11985071152, "load_duration": 98800094, "prompt_eval_count": 81, "prompt_eval_duration": 86284000, "eval_count": 512, "eval_duration": 11797629000, "timeToFirstTokenMs": 187.8317490000045 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 5, "valid": false, "attempts": [ { "measurement": { "total_duration": 12022516483, "load_duration": 122345293, "prompt_eval_count": 81, "prompt_eval_duration": 85808000, "eval_count": 512, "eval_duration": 11812279000, "timeToFirstTokenMs": 210.5972039999906 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 11999407439, "load_duration": 90688979, "prompt_eval_count": 81, "prompt_eval_duration": 85996000, "eval_count": 512, "eval_duration": 11820398000, "timeToFirstTokenMs": 179.32113699999172 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 11995588101, "load_duration": 119448183, "prompt_eval_count": 81, "prompt_eval_duration": 85243000, "eval_count": 512, "eval_duration": 11788779000, "timeToFirstTokenMs": 207.33334800001467 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 11995588101, "load_duration": 119448183, "prompt_eval_count": 81, "prompt_eval_duration": 85243000, "eval_count": 512, "eval_duration": 11788779000, "timeToFirstTokenMs": 207.33334800001467 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 81, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "failed": true } } }, "derived": { "generationTokensPerSecond": { "median": null, "coefficientOfVariation": null, "samples": 0 }, "prefillTokensPerSecond": { "median": 363.3433550394958, "coefficientOfVariation": 0.002852118811160864, "samples": 5 }, "timeToFirstTokenMs": { "median": null, "coefficientOfVariation": null, "samples": 0 }, "coldLoad": { "seconds": 3.657783694, "samples": 1 }, "passFailureRate": { "failedMeasuredPasses": 10, "totalMeasuredPasses": 16, "percent": 62.5 }, "attemptFailureRate": { "failedAttempts": 30, "totalAttempts": 36, "percent": 83.33333333333334 }, "roofline": { "modelWeightsGB": 20.274303147, "memoryBandwidthGBps": 760, "theoreticalMaxTokensPerSecond": 37.48587532156229, "utilization": null }, "diagnostics": [ { "id": "partial-cpu-offload", "status": "detected", "message": "58% of the model's resident bytes are on the host, not in VRAM", "evidence": { "source": "ollama.ps.size_vram", "granularity": "bytes", "residentBytes": 20691549392, "vramResidentBytes": 8704470547, "hostResidentBytes": 11987078845, "vramResidentFraction": 0.42067756174728127 } }, { "id": "context-vram-headroom", "status": "unavailable", "message": "Ollama /api/show does not expose the resolved KV-cache element type actually in use, so v1.1 does not calculate or threshold projected KV-cache VRAM", "evidence": { "configuredContext": 4096, "availableArchitectureMetadata": { "source": "ollama.show.model_info", "architecture": "laguna", "blockCount": 40, "kvHeadCount": 8, "attentionHeadCount": null, "embeddingLength": 2048, "headDimension": 128, "resolvedElementType": null, "projectedBytes": null, "calculationAvailable": false, "missingInputs": [ "resolvedKvCacheElementType" ] }, "missingInput": "resolvedKvCacheElementType" } }, { "id": "cpu-only-with-gpu", "status": "not-detected", "message": "42% of the model's resident bytes are in VRAM", "evidence": { "source": "ollama.ps.size_vram", "granularity": "bytes", "residentBytes": 20691549392, "vramResidentBytes": 8704470547, "hostResidentBytes": 11987078845, "vramResidentFraction": 0.42067756174728127, "gpuModel": "NVIDIA GeForce RTX 3080" } }, { "id": "weights-exceed-vram", "status": "detected", "message": "Quantized on-disk model weight size is larger than total VRAM", "evidence": { "weightsBytes": 20274303147, "totalVramBytes": 10737418240 } } ] } }