GLM-4.6V-Flash on Jetson AGX Orin 32GB Developer Kit — Q8_0, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

Model	GLM-4.6V-Flash
Parameters	10B
Device	Jetson AGX Orin 32GB Developer Kit
Quantization	Q8_0
Image size	720p
Images per camera	1
Max Cameras (response ≤ 3 s)	1
Engine	llama.cpp

Cameras	Response (s)	TPS (tok/s)	Target
1	2.93	16.1	≤3 s
2	3.14	8.0	>3 s
4	4.20	7.8	>3 s
8	21.5	8.0	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	2.93	16.1	≤3 s
2	5.84	15.6	>3 s
4	11.7	14.7	>3 s
8	24.0	13.1	>3 s
16	50.6	10.8	>3 s
32	—	—	Failed

GLM-4.6V-Flash (10B parameters), served in Q8_0 format with llama.cpp on Jetson AGX Orin 32GB Developer Kit, starts answering a single camera that sends one 720p image after 2.93 s, then writes 16.1 tok/s.

With 16 images per camera at 720p, the answer starts after 50.59 s. With one 2K image, after 15.55 s.

At the default target of an answer starting within 3 s (720p, one image per camera), it keeps up with one camera at a time.