VLM Inference Latency

Benchmarks

Dataset Name	SOTA Method	Metric	Trend
Jetson Orin llama.cpp quantization	LLaVA-v1.5-336	VE Latency (ms/patch)2.89		5	1mo ago
Qualcomm Snapdragon 8 Gen 3 SoC llama.cpp quantization	MobileVLM-336	VE Latency (ms/patch)6.82		5	1mo ago

Showing 2 of 2 rows