Qwen3.5-35B-A3B on Jetson AGX Orin 32GB Developer Kit — Q4_K_M, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

Model	Qwen3.5-35B-A3B
Parameters	35B
Device	Jetson AGX Orin 32GB Developer Kit
Quantization	Q4_K_M
Image size	720p
Images per camera	1
Max Cameras (response ≤ 3 s)	1
Engine	llama.cpp

Cameras	Response (s)	TPS (tok/s)	Target
1	2.81	30.5	≤3 s
2	4.74	25.0	>3 s
4	9.20	16.6	>3 s
8	25.4	18.6	>3 s

Images per request	Response (s)	TPS (tok/s)	Target
1	2.81	30.5	≤3 s
2	5.42	30.4	>3 s
4	10.6	30.2	>3 s
8	21.1	28.6	>3 s
16	42.6	26.2	>3 s
32	86.7	23.0	>3 s

Qwen3.5-35B-A3B (35B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin 32GB Developer Kit, starts answering a single camera that sends one 720p image after 2.81 s, then writes 30.5 tok/s.

With 32 images per camera at 720p, the answer starts after 86.68 s. With one 1080p image, after 7.93 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.