VLM Inference Benchmark Explorer

Qwen3.5-4B on Jetson AGX Orin 32GB — Q4_K_M, llama.cpp vision-language inference benchmark

Open this configuration in the VLM Inference Benchmark Explorer

ModelQwen3.5-4B
Parameters4.7B
DeviceJetson AGX Orin 32GB
QuantizationQ4_K_M
Image size720p
Images per camera1
Max Cameras (TTFT ≤ 3000 ms)1
Enginellama.cpp
CamerasTTFT (ms)TPS (tok/s)Target
1221025.3≤3000 ms
2357420.7>3000 ms
4715013.1>3000 ms
81474013.0>3000 ms
Images per requestTTFT (ms)TPS (tok/s)Target
1221025.3≤3000 ms
3631225.1>3000 ms
51038525.0>3000 ms

Qwen3.5-4B (4.7B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin 32GB, starts answering a single camera that sends one 720p image after 2,210 ms (time to first token, TTFT), then writes 25.3 tok/s.

With 5 images per camera at 720p, the answer starts after 10,385 ms. With one 2K image, after 12,483 ms.

At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), it keeps up with one camera at a time.