on-device-vs-cloud-llm-inference / results /fabian /stats_experiment_Llama-3-2-1B-Instruct-ONNX_always_device_once-per-sec_2025-12-03T20-58-00.csv
fhueni's picture
results: add results of three on device models
b8d240d
raw
history blame contribute delete
280 Bytes
route, total_requests, accuracy_percent, avg_latency_ms, avg_total_latency_ms, avg_queueing_time_ms, avg_inference_time_ms
overall, 500, 59.40, 1773.50, 196871.48, 195097.98, 1773.50
device, 500, 59.40, 1773.50, 196871.48, 195097.98, 1773.50
cloud, 0, 0.00, 0.00, 0.00, 0.00, 0.00