{ "protocolVersion": "osai-bench/1.3", "clientVersion": "0.10.0", "scoringVersion": "osai-bench-derive/1.3", "createdAt": "2026-08-07T07:55:10.817Z", "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": 9953733507, "vramResidentBytes": 8916178042, "hostResidentBytes": 1037555465, "vramResidentFraction": 0.8957621816707937 }, "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": "12th Gen Intel(R) Core(TM) i9-12900K" }, "gpu": { "present": true, "model": "NVIDIA GeForce RTX 3080", "totalVramBytes": 10737418240, "freeVramBytesAtCheck": 10326376448, "freeVramBytesAtLoad": 1286602752, "utilizationPercentAtCheck": 0, "driverVersion": "595.84", "provider": "nvidia-smi" }, "memory": { "totalBytes": 32817020928 }, "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": 3626561875, "load_duration": 3564056376, "prompt_eval_count": 34, "prompt_eval_duration": 60354000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 3628.6773159999993 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 3626561875, "load_duration": 3564056376, "prompt_eval_count": 34, "prompt_eval_duration": 60354000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 3628.6773159999993 }, "validity": { "valid": true, "reasons": [] } } ], "failed": false }, "w2": { "warmup": { "total_duration": 8022403241, "load_duration": 3733407300, "prompt_eval_count": 68, "prompt_eval_duration": 156566000, "eval_count": 128, "eval_duration": 4130031000, "timeToFirstTokenMs": 3893.9779909999997 }, "measuredPasses": [ { "index": 1, "valid": false, "attempts": [ { "measurement": { "total_duration": 4273762340, "load_duration": 114983816, "prompt_eval_count": 68, "prompt_eval_duration": 32780000, "eval_count": 128, "eval_duration": 4107785000, "timeToFirstTokenMs": 167.57838099999935 }, "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": 4275667952, "load_duration": 113935668, "prompt_eval_count": 68, "prompt_eval_duration": 32707000, "eval_count": 128, "eval_duration": 4110563000, "timeToFirstTokenMs": 166.14294399999926 }, "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": 4262239987, "load_duration": 121637699, "prompt_eval_count": 68, "prompt_eval_duration": 32831000, "eval_count": 128, "eval_duration": 4105511999, "timeToFirstTokenMs": 157.6559359999992 }, "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": 4262239987, "load_duration": 121637699, "prompt_eval_count": 68, "prompt_eval_duration": 32831000, "eval_count": 128, "eval_duration": 4105511999, "timeToFirstTokenMs": 157.6559359999992 }, "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": 4248090655, "load_duration": 116859821, "prompt_eval_count": 68, "prompt_eval_duration": 32708000, "eval_count": 128, "eval_duration": 4095981000, "timeToFirstTokenMs": 153.12508899999375 }, "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": 4267339157, "load_duration": 126259901, "prompt_eval_count": 68, "prompt_eval_duration": 32747999, "eval_count": 128, "eval_duration": 4106350000, "timeToFirstTokenMs": 161.88098300000274 }, "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": 4257748301, "load_duration": 123189201, "prompt_eval_count": 68, "prompt_eval_duration": 32777000, "eval_count": 128, "eval_duration": 4099479999, "timeToFirstTokenMs": 159.05186700000195 }, "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": 4257748301, "load_duration": 123189201, "prompt_eval_count": 68, "prompt_eval_duration": 32777000, "eval_count": 128, "eval_duration": 4099479999, "timeToFirstTokenMs": 159.05186700000195 }, "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": 4243258469, "load_duration": 117797784, "prompt_eval_count": 68, "prompt_eval_duration": 32753000, "eval_count": 128, "eval_duration": 4090462000, "timeToFirstTokenMs": 153.64439100000163 }, "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": 4263609993, "load_duration": 124069757, "prompt_eval_count": 68, "prompt_eval_duration": 32781999, "eval_count": 128, "eval_duration": 4104554000, "timeToFirstTokenMs": 159.9187479999964 }, "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": 4254533226, "load_duration": 121442553, "prompt_eval_count": 68, "prompt_eval_duration": 32662000, "eval_count": 128, "eval_duration": 4098054000, "timeToFirstTokenMs": 157.2348109999948 }, "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": 4254533226, "load_duration": 121442553, "prompt_eval_count": 68, "prompt_eval_duration": 32662000, "eval_count": 128, "eval_duration": 4098054000, "timeToFirstTokenMs": 157.2348109999948 }, "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": 4259421714, "load_duration": 121562904, "prompt_eval_count": 68, "prompt_eval_duration": 32826000, "eval_count": 128, "eval_duration": 4102844000, "timeToFirstTokenMs": 157.5016650000034 }, "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": 4265481442, "load_duration": 128821081, "prompt_eval_count": 68, "prompt_eval_duration": 32701000, "eval_count": 128, "eval_duration": 4102170000, "timeToFirstTokenMs": 164.05022499999905 }, "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": 4250559140, "load_duration": 113661474, "prompt_eval_count": 68, "prompt_eval_duration": 32802999, "eval_count": 128, "eval_duration": 4101078999, "timeToFirstTokenMs": 150.5090210000053 }, "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": 4250559140, "load_duration": 113661474, "prompt_eval_count": 68, "prompt_eval_duration": 32802999, "eval_count": 128, "eval_duration": 4101078999, "timeToFirstTokenMs": 150.5090210000053 }, "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": 4257490253, "load_duration": 120632319, "prompt_eval_count": 68, "prompt_eval_duration": 32807000, "eval_count": 128, "eval_duration": 4102261000, "timeToFirstTokenMs": 155.8946309999883 }, "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": 4253317802, "load_duration": 117856830, "prompt_eval_count": 68, "prompt_eval_duration": 32966000, "eval_count": 128, "eval_duration": 4100497999, "timeToFirstTokenMs": 153.63315100000182 }, "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": 4255994141, "load_duration": 121443360, "prompt_eval_count": 68, "prompt_eval_duration": 32802999, "eval_count": 128, "eval_duration": 4099465000, "timeToFirstTokenMs": 157.3571779999911 }, "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": 4255994141, "load_duration": 121443360, "prompt_eval_count": 68, "prompt_eval_duration": 32802999, "eval_count": 128, "eval_duration": 4099465000, "timeToFirstTokenMs": 157.3571779999911 }, "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": 1934532715, "load_duration": 118326853, "prompt_eval_count": 2815, "prompt_eval_duration": 1798505000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 1934.8413869999931 }, "measuredPasses": [ { "index": 1, "valid": true, "attempts": [ { "measurement": { "total_duration": 2165823916, "load_duration": 129780994, "prompt_eval_count": 2815, "prompt_eval_duration": 1783824000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2166.148576000007 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 2165823916, "load_duration": 129780994, "prompt_eval_count": 2815, "prompt_eval_duration": 1783824000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2166.148576000007 }, "validity": { "valid": true, "reasons": [] } }, { "index": 2, "valid": true, "attempts": [ { "measurement": { "total_duration": 2156271667, "load_duration": 117062776, "prompt_eval_count": 2815, "prompt_eval_duration": 1783629000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2156.5942989999894 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 2156271667, "load_duration": 117062776, "prompt_eval_count": 2815, "prompt_eval_duration": 1783629000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2156.5942989999894 }, "validity": { "valid": true, "reasons": [] } }, { "index": 3, "valid": true, "attempts": [ { "measurement": { "total_duration": 2157956799, "load_duration": 119976391, "prompt_eval_count": 2815, "prompt_eval_duration": 1784292000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2158.2082979999977 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 2157956799, "load_duration": 119976391, "prompt_eval_count": 2815, "prompt_eval_duration": 1784292000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2158.2082979999977 }, "validity": { "valid": true, "reasons": [] } }, { "index": 4, "valid": true, "attempts": [ { "measurement": { "total_duration": 2155630937, "load_duration": 121308551, "prompt_eval_count": 2815, "prompt_eval_duration": 1784719000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2156.1560829999944 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 2155630937, "load_duration": 121308551, "prompt_eval_count": 2815, "prompt_eval_duration": 1784719000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2156.1560829999944 }, "validity": { "valid": true, "reasons": [] } }, { "index": 5, "valid": true, "attempts": [ { "measurement": { "total_duration": 2153809128, "load_duration": 121109853, "prompt_eval_count": 2815, "prompt_eval_duration": 1783882000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2154.242506999988 }, "validity": { "valid": true, "reasons": [] } } ], "measurement": { "total_duration": 2153809128, "load_duration": 121109853, "prompt_eval_count": 2815, "prompt_eval_duration": 1783882000, "eval_count": 1, "eval_duration": 1000, "timeToFirstTokenMs": 2154.242506999988 }, "validity": { "valid": true, "reasons": [] } } ], "failed": false }, "w4": { "warmup": { "total_duration": 17165763473, "load_duration": 126959137, "prompt_eval_count": 68, "prompt_eval_duration": 34096000, "eval_count": 512, "eval_duration": 16762460000, "timeToFirstTokenMs": 404.1260970000003 }, "measuredPasses": [ { "index": 1, "valid": false, "attempts": [ { "measurement": { "total_duration": 16961228337, "load_duration": 118526417, "prompt_eval_count": 68, "prompt_eval_duration": 33978000, "eval_count": 512, "eval_duration": 16753790000, "timeToFirstTokenMs": 208.2717180000036 }, "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": 16922878477, "load_duration": 122178559, "prompt_eval_count": 68, "prompt_eval_duration": 34146000, "eval_count": 512, "eval_duration": 16764689999, "timeToFirstTokenMs": 159.28799300000537 }, "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": 16912171917, "load_duration": 126697724, "prompt_eval_count": 68, "prompt_eval_duration": 34094000, "eval_count": 512, "eval_duration": 16749596000, "timeToFirstTokenMs": 163.35971900000004 }, "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": 16912171917, "load_duration": 126697724, "prompt_eval_count": 68, "prompt_eval_duration": 34094000, "eval_count": 512, "eval_duration": 16749596000, "timeToFirstTokenMs": 163.35971900000004 }, "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": 16910996658, "load_duration": 121767104, "prompt_eval_count": 68, "prompt_eval_duration": 34080000, "eval_count": 512, "eval_duration": 16752879000, "timeToFirstTokenMs": 158.25539899998694 }, "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": 16906512467, "load_duration": 115229144, "prompt_eval_count": 68, "prompt_eval_duration": 34217000, "eval_count": 512, "eval_duration": 16754598999, "timeToFirstTokenMs": 152.54641900002025 }, "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": 16908521361, "load_duration": 124613989, "prompt_eval_count": 68, "prompt_eval_duration": 34246000, "eval_count": 512, "eval_duration": 16747667000, "timeToFirstTokenMs": 161.55281000002287 }, "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": 16908521361, "load_duration": 124613989, "prompt_eval_count": 68, "prompt_eval_duration": 34246000, "eval_count": 512, "eval_duration": 16747667000, "timeToFirstTokenMs": 161.55281000002287 }, "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": 16886981712, "load_duration": 120607682, "prompt_eval_count": 68, "prompt_eval_duration": 34181000, "eval_count": 512, "eval_duration": 16729790000, "timeToFirstTokenMs": 158.0440579999995 }, "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": 16910464572, "load_duration": 121584852, "prompt_eval_count": 68, "prompt_eval_duration": 34205000, "eval_count": 512, "eval_duration": 16752526000, "timeToFirstTokenMs": 158.76802899999893 }, "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": 16900988796, "load_duration": 113566083, "prompt_eval_count": 68, "prompt_eval_duration": 34152000, "eval_count": 512, "eval_duration": 16751116999, "timeToFirstTokenMs": 150.73461600000155 }, "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": 16900988796, "load_duration": 113566083, "prompt_eval_count": 68, "prompt_eval_duration": 34152000, "eval_count": 512, "eval_duration": 16751116999, "timeToFirstTokenMs": 150.73461600000155 }, "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": 16896835179, "load_duration": 114897154, "prompt_eval_count": 68, "prompt_eval_duration": 34078000, "eval_count": 512, "eval_duration": 16745669999, "timeToFirstTokenMs": 151.83632699999725 }, "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": 16918351723, "load_duration": 126407182, "prompt_eval_count": 68, "prompt_eval_duration": 34254000, "eval_count": 512, "eval_duration": 16755835000, "timeToFirstTokenMs": 163.38688700000057 }, "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": 16904400924, "load_duration": 113756462, "prompt_eval_count": 68, "prompt_eval_duration": 34358000, "eval_count": 512, "eval_duration": 16754240000, "timeToFirstTokenMs": 151.02916099998401 }, "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": 16904400924, "load_duration": 113756462, "prompt_eval_count": 68, "prompt_eval_duration": 34358000, "eval_count": 512, "eval_duration": 16754240000, "timeToFirstTokenMs": 151.02916099998401 }, "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": 16919095055, "load_duration": 122601869, "prompt_eval_count": 68, "prompt_eval_duration": 34328000, "eval_count": 512, "eval_duration": 16760152999, "timeToFirstTokenMs": 159.6158319999813 }, "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": 16895124373, "load_duration": 119565135, "prompt_eval_count": 68, "prompt_eval_duration": 34176000, "eval_count": 512, "eval_duration": 16739152999, "timeToFirstTokenMs": 156.8224240000127 }, "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": 16922050572, "load_duration": 127784535, "prompt_eval_count": 68, "prompt_eval_duration": 34098000, "eval_count": 512, "eval_duration": 16758308000, "timeToFirstTokenMs": 164.29736899997806 }, "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": 16922050572, "load_duration": 127784535, "prompt_eval_count": 68, "prompt_eval_duration": 34098000, "eval_count": 512, "eval_duration": 16758308000, "timeToFirstTokenMs": 164.29736899997806 }, "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": 1578.0191739139698, "coefficientOfVariation": 0.00024442345138699957, "samples": 5 }, "timeToFirstTokenMs": { "median": null, "coefficientOfVariation": null, "samples": 0 }, "coldLoad": { "seconds": 3.564056376, "samples": 1 }, "passFailureRate": { "failedMeasuredPasses": 10, "totalMeasuredPasses": 16, "percent": 62.5 }, "attemptFailureRate": { "failedAttempts": 30, "totalAttempts": 36, "percent": 83.33333333333334 }, "roofline": { "modelWeightsGB": 8.988124069, "memoryBandwidthGBps": 760, "theoreticalMaxTokensPerSecond": 84.55602016234252, "utilization": null }, "diagnostics": [ { "id": "partial-cpu-offload", "status": "detected", "message": "10% of the model's resident bytes are on the host, not in VRAM", "evidence": { "source": "ollama.ps.size_vram", "granularity": "bytes", "residentBytes": 9953733507, "vramResidentBytes": 8916178042, "hostResidentBytes": 1037555465, "vramResidentFraction": 0.8957621816707937 } }, { "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": "90% of the model's resident bytes are in VRAM", "evidence": { "source": "ollama.ps.size_vram", "granularity": "bytes", "residentBytes": 9953733507, "vramResidentBytes": 8916178042, "hostResidentBytes": 1037555465, "vramResidentFraction": 0.8957621816707937, "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": 8988124069, "totalVramBytes": 10737418240 } } ] } }