{ "protocolVersion": "osai-bench/1.3", "clientVersion": "0.12.0", "scoringVersion": "osai-bench-derive/1.4", "createdAt": "2026-10-20T06:24:53.647Z", "qualityOverride": true, "cohortEligible": false, "qualityConditions": [ { "code": "gpu-utilization", "detected": true } ], "runtime": { "name": "ollama", "version": "0.35.1", "endpoint": "loopback", "layerAssignment": null, "offloadPlacement": { "source": "ollama.ps.size_vram", "granularity": "bytes", "residentBytes": 9470098799, "vramResidentBytes": 9470098799, "hostResidentBytes": 0, "vramResidentFraction": 1 }, "kvCacheMetadata": { "source": "ollama.show.model_info", "architecture": "qwen2", "blockCount": 48, "kvHeadCount": 8, "attentionHeadCount": 40, "embeddingLength": 5120, "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": "qwen2.5:14b", "digest": "7cdf5a0187d5c58cc5d369b255592f7841d1c4696d45a8c8a9489440385b22f6", "family": "qwen2", "parameterSize": "14.8B", "quantization": "Q4_K_M", "weightsBytes": 8988124069, "weightsSource": "ollama.tags.size" }, "system": { "cpu": { "model": "Intel(R) Core(TM) i7-14700K" }, "gpu": { "present": true, "model": "NVIDIA GeForce RTX 4070 Ti", "totalVramBytes": 12878610432, "freeVramBytesAtCheck": 10959716352, "freeVramBytesAtLoad": 1990197248, "utilizationPercentAtCheck": 33, "driverVersion": "617.42", "provider": "nvidia-smi" }, "memory": { "totalBytes": 34018738176 }, "os": { "platform": "win32", "version": "10.0.26200", "architecture": "x64" }, "power": { "present": false, "onBattery": false } }, "configuration": { "memoryBandwidthGBps": 504, "memoryBandwidthSource": "manufacturer-table", "memoryBandwidthTableVersion": "osai-gpu-memory-bandwidth/2", "memoryBandwidthEntryId": "nvidia-geforce-rtx-4070-ti-12gb", "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": 5960399400, "load_duration": 5879600300, "prompt_eval_count": 34, "prompt_eval_duration": 78348000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 5960.9086, "timeToFirstVisibleTokenMs": 5960.9086 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 5960399400, "load_duration": 5879600300, "prompt_eval_count": 34, "prompt_eval_duration": 78348000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 5960.9086, "timeToFirstVisibleTokenMs": 5960.9086 }, "validity": { "valid": true, "reasons": [] } } ], "failed": false }, "w2": { "warmup": { "total_duration": 9979303500, "load_duration": 7050677000, "prompt_eval_count": 68, "prompt_eval_duration": 84667000, "eval_count": 128, "eval_duration": 2841621000, "timeToFirstTokenMs": 7138.023899999998, "timeToFirstVisibleTokenMs": 7138.023899999998 }, "measuredPasses": [ { "index": 1, "valid": false, "attempts": [ { "measurement": { "total_duration": 2892084900, "load_duration": 4125900, "prompt_eval_count": 68, "prompt_eval_duration": 22276000, "eval_count": 128, "eval_duration": 2849418000, "timeToFirstTokenMs": 42.647000000000844, "timeToFirstVisibleTokenMs": 42.647000000000844 }, "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": 2868725100, "load_duration": 2342200, "prompt_eval_count": 68, "prompt_eval_duration": 23782000, "eval_count": 128, "eval_duration": 2840959000, "timeToFirstTokenMs": 27.87120000000141, "timeToFirstVisibleTokenMs": 27.87120000000141 }, "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": 2843710200, "load_duration": 2243200, "prompt_eval_count": 68, "prompt_eval_duration": 22406000, "eval_count": 128, "eval_duration": 2817357000, "timeToFirstTokenMs": 26.79320000000007, "timeToFirstVisibleTokenMs": 26.79320000000007 }, "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": 2843710200, "load_duration": 2243200, "prompt_eval_count": 68, "prompt_eval_duration": 22406000, "eval_count": 128, "eval_duration": 2817357000, "timeToFirstTokenMs": 26.79320000000007, "timeToFirstVisibleTokenMs": 26.79320000000007 }, "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": 2893864300, "load_duration": 2593100, "prompt_eval_count": 68, "prompt_eval_duration": 23099000, "eval_count": 128, "eval_duration": 2865561000, "timeToFirstTokenMs": 28.176399999996647, "timeToFirstVisibleTokenMs": 28.176399999996647 }, "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": 3050376500, "load_duration": 2011800, "prompt_eval_count": 68, "prompt_eval_duration": 22233000, "eval_count": 128, "eval_duration": 3024840000, "timeToFirstTokenMs": 26.490600000004633, "timeToFirstVisibleTokenMs": 26.490600000004633 }, "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": 3067800300, "load_duration": 2067500, "prompt_eval_count": 68, "prompt_eval_duration": 23278000, "eval_count": 128, "eval_duration": 3040387000, "timeToFirstTokenMs": 27.67059999999765, "timeToFirstVisibleTokenMs": 27.67059999999765 }, "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": 3067800300, "load_duration": 2067500, "prompt_eval_count": 68, "prompt_eval_duration": 23278000, "eval_count": 128, "eval_duration": 3040387000, "timeToFirstTokenMs": 27.67059999999765, "timeToFirstVisibleTokenMs": 27.67059999999765 }, "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": 2847695400, "load_duration": 3970100, "prompt_eval_count": 68, "prompt_eval_duration": 24525000, "eval_count": 128, "eval_duration": 2816393000, "timeToFirstTokenMs": 31.51919999999518, "timeToFirstVisibleTokenMs": 31.51919999999518 }, "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": 2874432200, "load_duration": 4116300, "prompt_eval_count": 68, "prompt_eval_duration": 22315000, "eval_count": 128, "eval_duration": 2845988000, "timeToFirstTokenMs": 28.565200000004552, "timeToFirstVisibleTokenMs": 28.565200000004552 }, "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": 2878351400, "load_duration": 2069400, "prompt_eval_count": 68, "prompt_eval_duration": 22387000, "eval_count": 128, "eval_duration": 2853201000, "timeToFirstTokenMs": 26.37920000000304, "timeToFirstVisibleTokenMs": 26.37920000000304 }, "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": 2878351400, "load_duration": 2069400, "prompt_eval_count": 68, "prompt_eval_duration": 22387000, "eval_count": 128, "eval_duration": 2853201000, "timeToFirstTokenMs": 26.37920000000304, "timeToFirstVisibleTokenMs": 26.37920000000304 }, "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": 2816750200, "load_duration": 3113000, "prompt_eval_count": 68, "prompt_eval_duration": 22243000, "eval_count": 128, "eval_duration": 2789355000, "timeToFirstTokenMs": 27.620600000002014, "timeToFirstVisibleTokenMs": 27.620600000002014 }, "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": 2815459500, "load_duration": 2094600, "prompt_eval_count": 68, "prompt_eval_duration": 22533000, "eval_count": 128, "eval_duration": 2788276000, "timeToFirstTokenMs": 26.97830000000249, "timeToFirstVisibleTokenMs": 26.97830000000249 }, "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": 2850650100, "load_duration": 2079400, "prompt_eval_count": 68, "prompt_eval_duration": 22491000, "eval_count": 128, "eval_duration": 2824329000, "timeToFirstTokenMs": 26.350500000000466, "timeToFirstVisibleTokenMs": 26.350500000000466 }, "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": 2850650100, "load_duration": 2079400, "prompt_eval_count": 68, "prompt_eval_duration": 22491000, "eval_count": 128, "eval_duration": 2824329000, "timeToFirstTokenMs": 26.350500000000466, "timeToFirstVisibleTokenMs": 26.350500000000466 }, "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": 2949620500, "load_duration": 2072900, "prompt_eval_count": 68, "prompt_eval_duration": 22938000, "eval_count": 128, "eval_duration": 2922735000, "timeToFirstTokenMs": 26.85960000000341, "timeToFirstVisibleTokenMs": 26.85960000000341 }, "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": 2926144300, "load_duration": 2695400, "prompt_eval_count": 68, "prompt_eval_duration": 25007000, "eval_count": 128, "eval_duration": 2896312000, "timeToFirstTokenMs": 30.105100000000675, "timeToFirstVisibleTokenMs": 30.105100000000675 }, "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": 2870618300, "load_duration": 2906900, "prompt_eval_count": 68, "prompt_eval_duration": 22570000, "eval_count": 128, "eval_duration": 2843156000, "timeToFirstTokenMs": 27.340700000000652, "timeToFirstVisibleTokenMs": 27.340700000000652 }, "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": 2870618300, "load_duration": 2906900, "prompt_eval_count": 68, "prompt_eval_duration": 22570000, "eval_count": 128, "eval_duration": 2843156000, "timeToFirstTokenMs": 27.340700000000652, "timeToFirstVisibleTokenMs": 27.340700000000652 }, "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": 1037958600, "load_duration": 2603700, "prompt_eval_count": 2815, "prompt_eval_duration": 1022272000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1037.6587, "timeToFirstVisibleTokenMs": 1037.6587 }, "measuredPasses": [ { "index": 1, "valid": true, "attempts": [ { "measurement": { "total_duration": 1174804300, "load_duration": 3409200, "prompt_eval_count": 2815, "prompt_eval_duration": 997128000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1175.183600000004, "timeToFirstVisibleTokenMs": 1175.183600000004 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 1174804300, "load_duration": 3409200, "prompt_eval_count": 2815, "prompt_eval_duration": 997128000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1175.183600000004, "timeToFirstVisibleTokenMs": 1175.183600000004 }, "validity": { "valid": true, "reasons": [] } }, { "index": 2, "valid": true, "attempts": [ { "measurement": { "total_duration": 1175471200, "load_duration": 2306700, "prompt_eval_count": 2815, "prompt_eval_duration": 998351000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1175.5521000000008, "timeToFirstVisibleTokenMs": 1175.5521000000008 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 1175471200, "load_duration": 2306700, "prompt_eval_count": 2815, "prompt_eval_duration": 998351000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1175.5521000000008, "timeToFirstVisibleTokenMs": 1175.5521000000008 }, "validity": { "valid": true, "reasons": [] } }, { "index": 3, "valid": true, "attempts": [ { "measurement": { "total_duration": 1165521700, "load_duration": 2184200, "prompt_eval_count": 2815, "prompt_eval_duration": 994125000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1165.879700000005, "timeToFirstVisibleTokenMs": 1165.879700000005 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 1165521700, "load_duration": 2184200, "prompt_eval_count": 2815, "prompt_eval_duration": 994125000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1165.879700000005, "timeToFirstVisibleTokenMs": 1165.879700000005 }, "validity": { "valid": true, "reasons": [] } }, { "index": 4, "valid": true, "attempts": [ { "measurement": { "total_duration": 1165155800, "load_duration": 2873200, "prompt_eval_count": 2815, "prompt_eval_duration": 994210000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1165.1928000000044, "timeToFirstVisibleTokenMs": 1165.1928000000044 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 1165155800, "load_duration": 2873200, "prompt_eval_count": 2815, "prompt_eval_duration": 994210000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1165.1928000000044, "timeToFirstVisibleTokenMs": 1165.1928000000044 }, "validity": { "valid": true, "reasons": [] } }, { "index": 5, "valid": true, "attempts": [ { "measurement": { "total_duration": 1172506400, "load_duration": 2064700, "prompt_eval_count": 2815, "prompt_eval_duration": 994141000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1172.4586000000127, "timeToFirstVisibleTokenMs": 1172.4586000000127 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 1172506400, "load_duration": 2064700, "prompt_eval_count": 2815, "prompt_eval_duration": 994141000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1172.4586000000127, "timeToFirstVisibleTokenMs": 1172.4586000000127 }, "validity": { "valid": true, "reasons": [] } } ], "failed": false }, "w4": { "warmup": { "total_duration": 11498066600, "load_duration": 3218400, "prompt_eval_count": 68, "prompt_eval_duration": 24119000, "eval_count": 512, "eval_duration": 11301574000, "timeToFirstTokenMs": 195.39999999999418, "timeToFirstVisibleTokenMs": 195.39999999999418 }, "measuredPasses": [ { "index": 1, "valid": false, "attempts": [ { "measurement": { "total_duration": 11452486500, "load_duration": 2071100, "prompt_eval_count": 68, "prompt_eval_duration": 24433000, "eval_count": 512, "eval_duration": 11395954000, "timeToFirstTokenMs": 57.228900000001886, "timeToFirstVisibleTokenMs": 57.228900000001886 }, "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": 11585670500, "load_duration": 2569500, "prompt_eval_count": 68, "prompt_eval_duration": 24154000, "eval_count": 512, "eval_duration": 11557013000, "timeToFirstTokenMs": 28.69779999999446, "timeToFirstVisibleTokenMs": 28.69779999999446 }, "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": 11038451700, "load_duration": 2298700, "prompt_eval_count": 68, "prompt_eval_duration": 25096000, "eval_count": 512, "eval_duration": 11009668000, "timeToFirstTokenMs": 29.208400000003166, "timeToFirstVisibleTokenMs": 29.208400000003166 }, "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": 11038451700, "load_duration": 2298700, "prompt_eval_count": 68, "prompt_eval_duration": 25096000, "eval_count": 512, "eval_duration": 11009668000, "timeToFirstTokenMs": 29.208400000003166, "timeToFirstVisibleTokenMs": 29.208400000003166 }, "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": 11219696500, "load_duration": 2084800, "prompt_eval_count": 68, "prompt_eval_duration": 23223000, "eval_count": 512, "eval_duration": 11192437000, "timeToFirstTokenMs": 27.247500000012224, "timeToFirstVisibleTokenMs": 27.247500000012224 }, "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": 11173618600, "load_duration": 2080300, "prompt_eval_count": 68, "prompt_eval_duration": 22784000, "eval_count": 512, "eval_duration": 11146979000, "timeToFirstTokenMs": 26.73440000001574, "timeToFirstVisibleTokenMs": 26.73440000001574 }, "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": 11623481400, "load_duration": 2078600, "prompt_eval_count": 68, "prompt_eval_duration": 26281000, "eval_count": 512, "eval_duration": 11593294000, "timeToFirstTokenMs": 30.270199999999022, "timeToFirstVisibleTokenMs": 30.270199999999022 }, "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": 11623481400, "load_duration": 2078600, "prompt_eval_count": 68, "prompt_eval_duration": 26281000, "eval_count": 512, "eval_duration": 11593294000, "timeToFirstTokenMs": 30.270199999999022, "timeToFirstVisibleTokenMs": 30.270199999999022 }, "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": 11269174600, "load_duration": 1557100, "prompt_eval_count": 68, "prompt_eval_duration": 24429000, "eval_count": 512, "eval_duration": 11241048000, "timeToFirstTokenMs": 28.305200000002515, "timeToFirstVisibleTokenMs": 28.305200000002515 }, "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": 11658281600, "load_duration": 1543700, "prompt_eval_count": 68, "prompt_eval_duration": 23712000, "eval_count": 512, "eval_duration": 11630870000, "timeToFirstTokenMs": 27.691800000000512, "timeToFirstVisibleTokenMs": 27.691800000000512 }, "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": 11676287000, "load_duration": 2768000, "prompt_eval_count": 68, "prompt_eval_duration": 29293000, "eval_count": 512, "eval_duration": 11642009000, "timeToFirstTokenMs": 34.41770000001998, "timeToFirstVisibleTokenMs": 34.41770000001998 }, "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": 11676287000, "load_duration": 2768000, "prompt_eval_count": 68, "prompt_eval_duration": 29293000, "eval_count": 512, "eval_duration": 11642009000, "timeToFirstTokenMs": 34.41770000001998, "timeToFirstVisibleTokenMs": 34.41770000001998 }, "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": 11263185000, "load_duration": 2292000, "prompt_eval_count": 68, "prompt_eval_duration": 22788000, "eval_count": 512, "eval_duration": 11236380000, "timeToFirstTokenMs": 27.1079000000027, "timeToFirstVisibleTokenMs": 27.1079000000027 }, "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": 11163026800, "load_duration": 2095100, "prompt_eval_count": 68, "prompt_eval_duration": 26252000, "eval_count": 512, "eval_duration": 11132733000, "timeToFirstTokenMs": 30.33749999999418, "timeToFirstVisibleTokenMs": 30.33749999999418 }, "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": 11172607500, "load_duration": 2068800, "prompt_eval_count": 68, "prompt_eval_duration": 22880000, "eval_count": 512, "eval_duration": 11145412000, "timeToFirstTokenMs": 27.010999999998603, "timeToFirstVisibleTokenMs": 27.010999999998603 }, "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": 11172607500, "load_duration": 2068800, "prompt_eval_count": 68, "prompt_eval_duration": 22880000, "eval_count": 512, "eval_duration": 11145412000, "timeToFirstTokenMs": 27.010999999998603, "timeToFirstVisibleTokenMs": 27.010999999998603 }, "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": 11224463700, "load_duration": 2075000, "prompt_eval_count": 68, "prompt_eval_duration": 22726000, "eval_count": 512, "eval_duration": 11198305000, "timeToFirstTokenMs": 26.68859999999404, "timeToFirstVisibleTokenMs": 26.68859999999404 }, "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": 11288546100, "load_duration": 2049100, "prompt_eval_count": 68, "prompt_eval_duration": 22504000, "eval_count": 512, "eval_duration": 11261764000, "timeToFirstTokenMs": 26.653699999995297, "timeToFirstVisibleTokenMs": 26.653699999995297 }, "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": 10961198200, "load_duration": 2421200, "prompt_eval_count": 68, "prompt_eval_duration": 22666000, "eval_count": 512, "eval_duration": 10934391000, "timeToFirstTokenMs": 26.567500000004657, "timeToFirstVisibleTokenMs": 26.567500000004657 }, "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": 10961198200, "load_duration": 2421200, "prompt_eval_count": 68, "prompt_eval_duration": 22666000, "eval_count": 512, "eval_duration": 10934391000, "timeToFirstTokenMs": 26.567500000004657, "timeToFirstVisibleTokenMs": 26.567500000004657 }, "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": 2831.393769927882, "coefficientOfVariation": 0.0020155676017124236, "samples": 5 }, "timeToFirstTokenMs": { "median": null, "coefficientOfVariation": null, "samples": 0, "reasoningWithheldPasses": 0 }, "timeToFirstVisibleTokenMs": { "median": null, "coefficientOfVariation": null, "samples": 0 }, "coldLoad": { "seconds": 5.8796003, "samples": 1 }, "passFailureRate": { "failedMeasuredPasses": 10, "totalMeasuredPasses": 16, "percent": 62.5 }, "attemptFailureRate": { "failedAttempts": 30, "totalAttempts": 36, "percent": 83.33333333333334 }, "roofline": { "modelWeightsGB": 8.988124069, "memoryBandwidthGBps": 504, "theoreticalMaxTokensPerSecond": 56.073992318185034, "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": 9470098799, "vramResidentBytes": 9470098799, "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": 48, "kvHeadCount": 8, "attentionHeadCount": 40, "embeddingLength": 5120, "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": 9470098799, "vramResidentBytes": 9470098799, "hostResidentBytes": 0, "vramResidentFraction": 1, "gpuModel": "NVIDIA GeForce RTX 4070 Ti" } }, { "id": "weights-exceed-vram", "status": "not-detected", "message": "Quantized on-disk model weight size does not exceed total VRAM", "evidence": { "weightsBytes": 8988124069, "totalVramBytes": 12878610432 } } ] } }