on-device-vs-cloud-llm-inference
/
results
/fabian
/stats_experiment_granite-4-0-micro-ONNX-web_always_device_once-per-sec_2025-12-03T22-46-10.csv
| route, total_requests, accuracy_percent, avg_latency_ms, avg_total_latency_ms, avg_queueing_time_ms, avg_inference_time_ms | |
| overall, 500, 78.60, 7697.64, 1703783.31, 1696085.63, 7697.68 | |
| device, 500, 78.60, 7697.64, 1703783.31, 1696085.63, 7697.68 | |
| cloud, 0, 0.00, 0.00, 0.00, 0.00, 0.00 |