[ { "model": "qwen", "request": "../requests/speed-0-0.json", "answerText": "NOT RETAINED", "backgroundRows": 0, "repeat": 0, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 10.409972388995811, "firstEventSeconds": 0.63198247901164, "firstContentSeconds": 0.6319831690052524, "usage": { "completion_tokens": 128, "prompt_tokens": 84, "total_tokens": 212, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 84, "prompt_ms": 629.863, "prompt_per_token_ms": 7.4983690476190485, "prompt_per_second": 133.3623343488981, "predicted_n": 128, "predicted_ms": 9777.915, "predicted_per_token_ms": 76.99145669291339, "predicted_per_second": 12.988454082491002 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-0-0.json", "answerText": "NOT RETAINED", "backgroundRows": 0, "repeat": 0, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 7.83752790701692, "firstEventSeconds": 4.170653588022105, "firstContentSeconds": 4.1706542180036195, "usage": { "prompt_tokens": 84, "completion_tokens": 128, "total_tokens": 212, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 84, "prompt_ms": 4141.6, "prompt_per_token_ms": 49.305, "prompt_per_second": 20.3, "predicted_n": 128, "predicted_ms": 3693.5, "predicted_per_token_ms": 28.855, "predicted_per_second": 34.7, "draft_n": 109, "draft_n_accepted": 82 }, "finishReason": "length" }, { "model": "qwen", "request": "../requests/speed-0-1.json", "answerText": "NOT RETAINED", "backgroundRows": 0, "repeat": 1, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 10.398761485004798, "firstEventSeconds": 0.6309352309908718, "firstContentSeconds": 0.6309355410048738, "usage": { "completion_tokens": 128, "prompt_tokens": 84, "total_tokens": 212, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 84, "prompt_ms": 629.149, "prompt_per_token_ms": 7.489869047619048, "prompt_per_second": 133.51368276831084, "predicted_n": 128, "predicted_ms": 9767.716, "predicted_per_token_ms": 76.91114960629922, "predicted_per_second": 13.002016029131067 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-0-1.json", "answerText": "NOT RETAINED", "backgroundRows": 0, "repeat": 1, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 3.4626010450010654, "firstEventSeconds": 1.8052194040210452, "firstContentSeconds": 1.8052198940131348, "usage": { "prompt_tokens": 84, "completion_tokens": 128, "total_tokens": 212, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 84, "prompt_ms": 1785.0, "prompt_per_token_ms": 21.25, "prompt_per_second": 47.1, "predicted_n": 128, "predicted_ms": 1675.7, "predicted_per_token_ms": 13.091, "predicted_per_second": 76.4, "draft_n": 112, "draft_n_accepted": 85 }, "finishReason": "length" }, { "model": "qwen", "request": "../requests/speed-0-2.json", "answerText": "NOT RETAINED", "backgroundRows": 0, "repeat": 2, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 10.390896266995696, "firstEventSeconds": 0.6332307089760434, "firstContentSeconds": 0.6332310089783277, "usage": { "completion_tokens": 128, "prompt_tokens": 84, "total_tokens": 212, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 84, "prompt_ms": 631.15, "prompt_per_token_ms": 7.513690476190476, "prompt_per_second": 133.0903905569199, "predicted_n": 128, "predicted_ms": 9757.594, "predicted_per_token_ms": 76.83144881889763, "predicted_per_second": 13.015503616977712 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-0-2.json", "answerText": "NOT RETAINED", "backgroundRows": 0, "repeat": 2, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 4.369044443999883, "firstEventSeconds": 1.7186729999957606, "firstContentSeconds": 1.71867381001357, "usage": { "prompt_tokens": 84, "completion_tokens": 128, "total_tokens": 212, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 84, "prompt_ms": 1698.6, "prompt_per_token_ms": 20.221, "prompt_per_second": 49.5, "predicted_n": 128, "predicted_ms": 2668.5, "predicted_per_token_ms": 20.848, "predicted_per_second": 48.0, "draft_n": 114, "draft_n_accepted": 57 }, "finishReason": "length" }, { "model": "qwen", "request": "../requests/speed-500-0.json", "answerText": "NOT RETAINED", "backgroundRows": 500, "repeat": 0, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 21.304412265017163, "firstEventSeconds": 11.251485371001763, "firstContentSeconds": 11.251485861022957, "usage": { "completion_tokens": 128, "prompt_tokens": 6586, "total_tokens": 6714, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 6586, "prompt_ms": 11243.521, "prompt_per_token_ms": 1.707185089583966, "prompt_per_second": 585.7595676656805, "predicted_n": 128, "predicted_ms": 10052.93, "predicted_per_token_ms": 79.15692913385827, "predicted_per_second": 12.633132827941704 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-500-0.json", "answerText": "NOT RETAINED", "backgroundRows": 500, "repeat": 0, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 23.170635463000508, "firstEventSeconds": 21.384141315997113, "firstContentSeconds": 21.384142135997536, "usage": { "prompt_tokens": 6586, "completion_tokens": 128, "total_tokens": 6714, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 6586, "prompt_ms": 21346.0, "prompt_per_token_ms": 3.241, "prompt_per_second": 308.5, "predicted_n": 128, "predicted_ms": 1818.9, "predicted_per_token_ms": 14.21, "predicted_per_second": 70.4, "draft_n": 108, "draft_n_accepted": 71 }, "finishReason": "length" }, { "model": "qwen", "request": "../requests/speed-500-1.json", "answerText": "NOT RETAINED", "backgroundRows": 500, "repeat": 1, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 21.29453315201681, "firstEventSeconds": 11.262291151011596, "firstContentSeconds": 11.26229199100635, "usage": { "completion_tokens": 128, "prompt_tokens": 6586, "total_tokens": 6714, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 6586, "prompt_ms": 11254.487, "prompt_per_token_ms": 1.7088501366535074, "prompt_per_second": 585.188822911253, "predicted_n": 128, "predicted_ms": 10032.146, "predicted_per_token_ms": 78.99327559055119, "predicted_per_second": 12.659305396871218 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-500-1.json", "answerText": "NOT RETAINED", "backgroundRows": 500, "repeat": 1, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 14.495574722997844, "firstEventSeconds": 12.934984580992023, "firstContentSeconds": 12.934985511004925, "usage": { "prompt_tokens": 6586, "completion_tokens": 128, "total_tokens": 6714, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 6586, "prompt_ms": 12902.6, "prompt_per_token_ms": 1.959, "prompt_per_second": 510.4, "predicted_n": 128, "predicted_ms": 1588.7, "predicted_per_token_ms": 12.412, "predicted_per_second": 80.6, "draft_n": 117, "draft_n_accepted": 82 }, "finishReason": "length" }, { "model": "qwen", "request": "../requests/speed-500-2.json", "answerText": "NOT RETAINED", "backgroundRows": 500, "repeat": 2, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 21.26456801700988, "firstEventSeconds": 11.242676620022394, "firstContentSeconds": 11.2426774300111, "usage": { "completion_tokens": 128, "prompt_tokens": 6586, "total_tokens": 6714, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 6586, "prompt_ms": 11234.29, "prompt_per_token_ms": 1.705783480109323, "prompt_per_second": 586.2408750352714, "predicted_n": 128, "predicted_ms": 10021.888, "predicted_per_token_ms": 78.91250393700788, "predicted_per_second": 12.67226295085317 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-500-2.json", "answerText": "NOT RETAINED", "backgroundRows": 500, "repeat": 2, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 14.579910433996702, "firstEventSeconds": 12.770520026999293, "firstContentSeconds": 12.770520866994048, "usage": { "prompt_tokens": 6586, "completion_tokens": 128, "total_tokens": 6714, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 6586, "prompt_ms": 12738.0, "prompt_per_token_ms": 1.934, "prompt_per_second": 517.0, "predicted_n": 128, "predicted_ms": 1837.0, "predicted_per_token_ms": 14.352, "predicted_per_second": 69.7, "draft_n": 104, "draft_n_accepted": 70 }, "finishReason": "length" }, { "model": "qwen", "request": "../requests/speed-2000-0.json", "answerText": "NOT RETAINED", "backgroundRows": 2000, "repeat": 0, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 56.980559170013294, "firstEventSeconds": 46.11016746799578, "firstContentSeconds": 46.11016790801659, "usage": { "completion_tokens": 128, "prompt_tokens": 26087, "total_tokens": 26215, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 26087, "prompt_ms": 46085.009, "prompt_per_token_ms": 1.7665890673515543, "prompt_per_second": 566.0625996622892, "predicted_n": 128, "predicted_ms": 10870.271, "predicted_per_token_ms": 85.59268503937008, "predicted_per_second": 11.683241383770469 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-2000-0.json", "answerText": "NOT RETAINED", "backgroundRows": 2000, "repeat": 0, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 33.09755272499751, "firstEventSeconds": 31.31999398302287, "firstContentSeconds": 31.31999467301648, "usage": { "prompt_tokens": 26087, "completion_tokens": 128, "total_tokens": 26215, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 26087, "prompt_ms": 31214.1, "prompt_per_token_ms": 1.197, "prompt_per_second": 835.7, "predicted_n": 128, "predicted_ms": 1806.0, "predicted_per_token_ms": 14.109, "predicted_per_second": 70.9, "draft_n": 106, "draft_n_accepted": 72 }, "finishReason": "length" }, { "model": "qwen", "request": "../requests/speed-2000-1.json", "answerText": "NOT RETAINED", "backgroundRows": 2000, "repeat": 1, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 56.6272670670005, "firstEventSeconds": 45.6564757929882, "firstContentSeconds": 45.6564762830094, "usage": { "completion_tokens": 128, "prompt_tokens": 26087, "total_tokens": 26215, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 26087, "prompt_ms": 45630.789, "prompt_per_token_ms": 1.7491773297044504, "prompt_per_second": 571.6973248040923, "predicted_n": 128, "predicted_ms": 10970.69, "predicted_per_token_ms": 86.38338582677166, "predicted_per_second": 11.576300123328615 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-2000-1.json", "answerText": "NOT RETAINED", "backgroundRows": 2000, "repeat": 1, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 33.11324697799864, "firstEventSeconds": 31.33909166799276, "firstContentSeconds": 31.339092177979182, "usage": { "prompt_tokens": 26087, "completion_tokens": 128, "total_tokens": 26215, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 26087, "prompt_ms": 31300.9, "prompt_per_token_ms": 1.2, "prompt_per_second": 833.4, "predicted_n": 128, "predicted_ms": 1802.2, "predicted_per_token_ms": 14.08, "predicted_per_second": 71.0, "draft_n": 111, "draft_n_accepted": 73 }, "finishReason": "length" }, { "model": "qwen", "request": "../requests/speed-2000-2.json", "answerText": "NOT RETAINED", "backgroundRows": 2000, "repeat": 2, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 57.09160934301326, "firstEventSeconds": 46.20735920700827, "firstContentSeconds": 46.20735965701169, "usage": { "completion_tokens": 128, "prompt_tokens": 26087, "total_tokens": 26215, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 26087, "prompt_ms": 46180.92, "prompt_per_token_ms": 1.7702656495572506, "prompt_per_second": 564.886970636358, "predicted_n": 128, "predicted_ms": 10884.104, "predicted_per_token_ms": 85.7016062992126, "predicted_per_second": 11.66839273127122 }, "finishReason": "length" }, { "model": "strata", "request": "../requests/speed-2000-2.json", "answerText": "NOT RETAINED", "backgroundRows": 2000, "repeat": 2, "thinking": false, "requestedOutputTokens": 128, "reasoningChars": 0, "elapsedSeconds": 32.990750141005265, "firstEventSeconds": 31.257208458002424, "firstContentSeconds": 31.257209008006612, "usage": { "prompt_tokens": 26087, "completion_tokens": 128, "total_tokens": 26215, "prompt_tokens_details": { "cached_tokens": 0 } }, "timings": { "cache_n": 0, "prompt_n": 26087, "prompt_ms": 31218.5, "prompt_per_token_ms": 1.197, "prompt_per_second": 835.6, "predicted_n": 128, "predicted_ms": 1761.2, "predicted_per_token_ms": 13.759, "predicted_per_second": 72.7, "draft_n": 125, "draft_n_accepted": 78 }, "finishReason": "length" } ]