ResearchDatasetsQwen2.5-VLQwen2.5-VLFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsInference Latency EvaluationQwen2.5-VL on NVIDIA Jetson Orin NX 8GB inference 0.5B42.5Prefill Latency4
Inference Latency EvaluationQwen2.5-VL on NVIDIA Jetson Orin NX 8GB inference 0.5B42.5Prefill Latency4