{ "protocolVersion": "osai-bench/1.3", "clientVersion": "0.10.0", "scoringVersion": "osai-bench-derive/1.3", "createdAt": "2026-08-03T06:06:31.637Z", "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": 7891006258, "vramResidentBytes": 7891006258, "hostResidentBytes": 0, "vramResidentFraction": 1 }, "kvCacheMetadata": { "source": "ollama.show.model_info", "architecture": "qwen2", "blockCount": 28, "kvHeadCount": 4, "attentionHeadCount": 28, "embeddingLength": 3584, "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": "qwen2.5:7b-instruct-q8_0", "digest": "2d9500c948416525a044cc51a47a1ef93deb045aebf2f61e8d6b3ac3a3cf2290", "family": "qwen2", "parameterSize": "7.6B", "quantization": "Q8_0", "weightsBytes": 8098538978, "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": 10311696384, "freeVramBytesAtLoad": 2372927488, "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": 8437951571, "load_duration": 8395862104, "prompt_eval_count": 34, "prompt_eval_duration": 39336000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 8439.747659 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 8437951571, "load_duration": 8395862104, "prompt_eval_count": 34, "prompt_eval_duration": 39336000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 8439.747659 }, "validity": { "valid": true, "reasons": [] } } ], "failed": false }, "w2": { "warmup": { "total_duration": 9815690759, "load_duration": 8148842764, "prompt_eval_count": 68, "prompt_eval_duration": 45429000, "eval_count": 128, "eval_duration": 1618116000, "timeToFirstTokenMs": 8199.184759 }, "measuredPasses": [ { "index": 1, "valid": false, "attempts": [ { "measurement": { "total_duration": 1771097421, "load_duration": 148671378, "prompt_eval_count": 68, "prompt_eval_duration": 12782000, "eval_count": 128, "eval_duration": 1598613000, "timeToFirstTokenMs": 172.95331600000281 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1776021851, "load_duration": 147674971, "prompt_eval_count": 68, "prompt_eval_duration": 12814000, "eval_count": 128, "eval_duration": 1600613000, "timeToFirstTokenMs": 175.7328170000037 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1745836170, "load_duration": 127857475, "prompt_eval_count": 68, "prompt_eval_duration": 12802000, "eval_count": 128, "eval_duration": 1602964000, "timeToFirstTokenMs": 143.2619210000048 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 1745836170, "load_duration": 127857475, "prompt_eval_count": 68, "prompt_eval_duration": 12802000, "eval_count": 128, "eval_duration": 1602964000, "timeToFirstTokenMs": 143.2619210000048 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 2, "valid": false, "attempts": [ { "measurement": { "total_duration": 1754223630, "load_duration": 136422020, "prompt_eval_count": 68, "prompt_eval_duration": 12907000, "eval_count": 128, "eval_duration": 1602251000, "timeToFirstTokenMs": 152.25893400000496 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1765563966, "load_duration": 146661556, "prompt_eval_count": 68, "prompt_eval_duration": 13047000, "eval_count": 128, "eval_duration": 1603764000, "timeToFirstTokenMs": 162.29683300000033 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1763851579, "load_duration": 145207204, "prompt_eval_count": 68, "prompt_eval_duration": 12834000, "eval_count": 128, "eval_duration": 1603676000, "timeToFirstTokenMs": 160.531207 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 1763851579, "load_duration": 145207204, "prompt_eval_count": 68, "prompt_eval_duration": 12834000, "eval_count": 128, "eval_duration": 1603676000, "timeToFirstTokenMs": 160.531207 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 3, "valid": false, "attempts": [ { "measurement": { "total_duration": 1775370104, "load_duration": 158021336, "prompt_eval_count": 68, "prompt_eval_duration": 12927000, "eval_count": 128, "eval_duration": 1602395000, "timeToFirstTokenMs": 173.4216349999988 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1743127448, "load_duration": 127070154, "prompt_eval_count": 68, "prompt_eval_duration": 12759000, "eval_count": 128, "eval_duration": 1601078000, "timeToFirstTokenMs": 142.4488610000044 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1763516130, "load_duration": 146625268, "prompt_eval_count": 68, "prompt_eval_duration": 12825000, "eval_count": 128, "eval_duration": 1601795000, "timeToFirstTokenMs": 162.12907100000302 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 1763516130, "load_duration": 146625268, "prompt_eval_count": 68, "prompt_eval_duration": 12825000, "eval_count": 128, "eval_duration": 1601795000, "timeToFirstTokenMs": 162.12907100000302 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 4, "valid": false, "attempts": [ { "measurement": { "total_duration": 1768603109, "load_duration": 152002490, "prompt_eval_count": 68, "prompt_eval_duration": 12789000, "eval_count": 128, "eval_duration": 1601692000, "timeToFirstTokenMs": 167.16424499999994 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1746406021, "load_duration": 131039993, "prompt_eval_count": 68, "prompt_eval_duration": 13080000, "eval_count": 128, "eval_duration": 1599757000, "timeToFirstTokenMs": 146.95026199999847 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1774733302, "load_duration": 159943496, "prompt_eval_count": 68, "prompt_eval_duration": 12870000, "eval_count": 128, "eval_duration": 1599968000, "timeToFirstTokenMs": 175.14207200000237 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 1774733302, "load_duration": 159943496, "prompt_eval_count": 68, "prompt_eval_duration": 12870000, "eval_count": 128, "eval_duration": 1599968000, "timeToFirstTokenMs": 175.14207200000237 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 5, "valid": false, "attempts": [ { "measurement": { "total_duration": 1754770438, "load_duration": 139585660, "prompt_eval_count": 68, "prompt_eval_duration": 12744000, "eval_count": 128, "eval_duration": 1600369000, "timeToFirstTokenMs": 154.81807199999457 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1751566569, "load_duration": 134227194, "prompt_eval_count": 68, "prompt_eval_duration": 12878000, "eval_count": 128, "eval_duration": 1602384000, "timeToFirstTokenMs": 149.5314290000024 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 1784267650, "load_duration": 163222583, "prompt_eval_count": 68, "prompt_eval_duration": 12861000, "eval_count": 128, "eval_duration": 1605867000, "timeToFirstTokenMs": 178.5666579999961 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 1784267650, "load_duration": 163222583, "prompt_eval_count": 68, "prompt_eval_duration": 12861000, "eval_count": 128, "eval_duration": 1605867000, "timeToFirstTokenMs": 178.5666579999961 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "failed": true }, "w3": { "warmup": { "total_duration": 748192415, "load_duration": 136530861, "prompt_eval_count": 2815, "prompt_eval_duration": 577943000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 748.442974000005 }, "measuredPasses": [ { "index": 1, "valid": true, "attempts": [ { "measurement": { "total_duration": 835333481, "load_duration": 124075874, "prompt_eval_count": 2815, "prompt_eval_duration": 574636000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 835.6884110000028 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 835333481, "load_duration": 124075874, "prompt_eval_count": 2815, "prompt_eval_duration": 574636000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 835.6884110000028 }, "validity": { "valid": true, "reasons": [] } }, { "index": 2, "valid": true, "attempts": [ { "measurement": { "total_duration": 892008080, "load_duration": 146941683, "prompt_eval_count": 2815, "prompt_eval_duration": 569668000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 892.3851809999978 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 892008080, "load_duration": 146941683, "prompt_eval_count": 2815, "prompt_eval_duration": 569668000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 892.3851809999978 }, "validity": { "valid": true, "reasons": [] } }, { "index": 3, "valid": true, "attempts": [ { "measurement": { "total_duration": 838056422, "load_duration": 123567234, "prompt_eval_count": 2815, "prompt_eval_duration": 568449000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 838.4080160000012 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 838056422, "load_duration": 123567234, "prompt_eval_count": 2815, "prompt_eval_duration": 568449000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 838.4080160000012 }, "validity": { "valid": true, "reasons": [] } }, { "index": 4, "valid": true, "attempts": [ { "measurement": { "total_duration": 827965964, "load_duration": 127314597, "prompt_eval_count": 2815, "prompt_eval_duration": 565452000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 828.4516399999993 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 827965964, "load_duration": 127314597, "prompt_eval_count": 2815, "prompt_eval_duration": 565452000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 828.4516399999993 }, "validity": { "valid": true, "reasons": [] } }, { "index": 5, "valid": true, "attempts": [ { "measurement": { "total_duration": 829992106, "load_duration": 133051545, "prompt_eval_count": 2815, "prompt_eval_duration": 568211000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 830.3598610000045 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 829992106, "load_duration": 133051545, "prompt_eval_count": 2815, "prompt_eval_duration": 568211000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 830.3598610000045 }, "validity": { "valid": true, "reasons": [] } } ], "failed": false }, "w4": { "warmup": { "total_duration": 6725363950, "load_duration": 122850192, "prompt_eval_count": 68, "prompt_eval_duration": 13625000, "eval_count": 512, "eval_duration": 6459840000, "timeToFirstTokenMs": 265.89891499999794 }, "measuredPasses": [ { "index": 1, "valid": false, "attempts": [ { "measurement": { "total_duration": 6657398776, "load_duration": 139408368, "prompt_eval_count": 68, "prompt_eval_duration": 13775000, "eval_count": 512, "eval_duration": 6470589000, "timeToFirstTokenMs": 187.28809999999066 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6633541040, "load_duration": 146889078, "prompt_eval_count": 68, "prompt_eval_duration": 14018000, "eval_count": 512, "eval_duration": 6470574000, "timeToFirstTokenMs": 163.2559850000107 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6612194567, "load_duration": 124508693, "prompt_eval_count": 68, "prompt_eval_duration": 13903000, "eval_count": 512, "eval_duration": 6472048000, "timeToFirstTokenMs": 140.68157100000826 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 6612194567, "load_duration": 124508693, "prompt_eval_count": 68, "prompt_eval_duration": 13903000, "eval_count": 512, "eval_duration": 6472048000, "timeToFirstTokenMs": 140.68157100000826 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 2, "valid": false, "attempts": [ { "measurement": { "total_duration": 6636348861, "load_duration": 145568714, "prompt_eval_count": 68, "prompt_eval_duration": 13840000, "eval_count": 512, "eval_duration": 6475292000, "timeToFirstTokenMs": 161.39681600000768 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6642256427, "load_duration": 146619683, "prompt_eval_count": 68, "prompt_eval_duration": 14173000, "eval_count": 512, "eval_duration": 6478356000, "timeToFirstTokenMs": 164.08317100000568 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6624919815, "load_duration": 130852486, "prompt_eval_count": 68, "prompt_eval_duration": 13871000, "eval_count": 512, "eval_duration": 6478349000, "timeToFirstTokenMs": 146.95558600001095 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 6624919815, "load_duration": 130852486, "prompt_eval_count": 68, "prompt_eval_duration": 13871000, "eval_count": 512, "eval_duration": 6478349000, "timeToFirstTokenMs": 146.95558600001095 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 3, "valid": false, "attempts": [ { "measurement": { "total_duration": 6620506938, "load_duration": 126837391, "prompt_eval_count": 68, "prompt_eval_duration": 14017000, "eval_count": 512, "eval_duration": 6477722000, "timeToFirstTokenMs": 143.0246049999987 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6661327709, "load_duration": 165513423, "prompt_eval_count": 68, "prompt_eval_duration": 13826000, "eval_count": 512, "eval_duration": 6480345000, "timeToFirstTokenMs": 181.3767680000019 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6674195595, "load_duration": 162744472, "prompt_eval_count": 68, "prompt_eval_duration": 14377000, "eval_count": 512, "eval_duration": 6494089000, "timeToFirstTokenMs": 180.37575400000787 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 6674195595, "load_duration": 162744472, "prompt_eval_count": 68, "prompt_eval_duration": 14377000, "eval_count": 512, "eval_duration": 6494089000, "timeToFirstTokenMs": 180.37575400000787 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 4, "valid": false, "attempts": [ { "measurement": { "total_duration": 6631992474, "load_duration": 138619187, "prompt_eval_count": 68, "prompt_eval_duration": 13868000, "eval_count": 512, "eval_duration": 6476241000, "timeToFirstTokenMs": 156.2662810000038 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6613943191, "load_duration": 132361333, "prompt_eval_count": 68, "prompt_eval_duration": 13886000, "eval_count": 512, "eval_duration": 6465611000, "timeToFirstTokenMs": 148.6708370000124 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6629510380, "load_duration": 128622062, "prompt_eval_count": 68, "prompt_eval_duration": 13860000, "eval_count": 512, "eval_duration": 6484870000, "timeToFirstTokenMs": 144.93437400000403 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 6629510380, "load_duration": 128622062, "prompt_eval_count": 68, "prompt_eval_duration": 13860000, "eval_count": 512, "eval_duration": 6484870000, "timeToFirstTokenMs": 144.93437400000403 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "index": 5, "valid": false, "attempts": [ { "measurement": { "total_duration": 6640843321, "load_duration": 139389313, "prompt_eval_count": 68, "prompt_eval_duration": 13629000, "eval_count": 512, "eval_duration": 6486221000, "timeToFirstTokenMs": 154.9927219999954 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6619018080, "load_duration": 141589565, "prompt_eval_count": 68, "prompt_eval_duration": 13875000, "eval_count": 512, "eval_duration": 6461236000, "timeToFirstTokenMs": 158.01779400001396 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } }, { "measurement": { "total_duration": 6641450073, "load_duration": 149161804, "prompt_eval_count": 68, "prompt_eval_duration": 13860000, "eval_count": 512, "eval_duration": 6475615000, "timeToFirstTokenMs": 166.18819400001667 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "measurement": { "total_duration": 6641450073, "load_duration": 149161804, "prompt_eval_count": 68, "prompt_eval_duration": 13860000, "eval_count": 512, "eval_duration": 6475615000, "timeToFirstTokenMs": 166.18819400001667 }, "validity": { "valid": false, "reasons": [ { "code": "prompt-count-out-of-range", "expectedMin": 20, "expectedMax": 64, "actual": 68, "message": "prompt_eval_count must fall between 20 and 64 tokens" } ] } } ], "failed": true } } }, "derived": { "generationTokensPerSecond": { "median": null, "coefficientOfVariation": null, "samples": 0 }, "prefillTokensPerSecond": { "median": 4952.071337974031, "coefficientOfVariation": 0.005891459148234958, "samples": 5 }, "timeToFirstTokenMs": { "median": null, "coefficientOfVariation": null, "samples": 0 }, "coldLoad": { "seconds": 8.395862104, "samples": 1 }, "passFailureRate": { "failedMeasuredPasses": 10, "totalMeasuredPasses": 16, "percent": 62.5 }, "attemptFailureRate": { "failedAttempts": 30, "totalAttempts": 36, "percent": 83.33333333333334 }, "roofline": { "modelWeightsGB": 8.098538978, "memoryBandwidthGBps": 760, "theoreticalMaxTokensPerSecond": 93.84408744152122, "utilization": null }, "diagnostics": [ { "id": "partial-cpu-offload", "status": "not-detected", "message": "The whole resident footprint is on one side; no split between VRAM and host memory", "evidence": { "source": "ollama.ps.size_vram", "granularity": "bytes", "residentBytes": 7891006258, "vramResidentBytes": 7891006258, "hostResidentBytes": 0, "vramResidentFraction": 1 } }, { "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": "qwen2", "blockCount": 28, "kvHeadCount": 4, "attentionHeadCount": 28, "embeddingLength": 3584, "headDimension": 128, "resolvedElementType": null, "projectedBytes": null, "calculationAvailable": false, "missingInputs": [ "resolvedKvCacheElementType" ] }, "missingInput": "resolvedKvCacheElementType" } }, { "id": "cpu-only-with-gpu", "status": "not-detected", "message": "100% of the model's resident bytes are in VRAM", "evidence": { "source": "ollama.ps.size_vram", "granularity": "bytes", "residentBytes": 7891006258, "vramResidentBytes": 7891006258, "hostResidentBytes": 0, "vramResidentFraction": 1, "gpuModel": "NVIDIA GeForce RTX 3080" } }, { "id": "weights-exceed-vram", "status": "not-detected", "message": "Quantized on-disk model weight size does not exceed total VRAM", "evidence": { "weightsBytes": 8098538978, "totalVramBytes": 10737418240 } } ] } }