VLM Inference Benchmark Explorer
Qwen3.5-4B on Jetson AGX Orin — Q4_K_M, llama.cpp vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Qwen3.5-4B |
|---|---|
| Parameters | 4.7B |
| Device | Jetson AGX Orin |
| Quantization | Q4_K_M |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (response ≤ 3 s) | 2 |
| Engine | llama.cpp |
| Cameras | Response (s) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 1.57 | 33.6 | PASS |
| 2 | 2.50 | 18.2 | PASS |
| 4 | 5.16 | 11.0 | FAIL |
| 8 | 10.1 | 16.0 | FAIL |
Qwen3.5-4B (4.7B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin, starts answering a single camera that sends one 720p image after 1.57 s, then writes 33.6 tok/s.
With 5 images per camera at 720p, the answer starts after 7.14 s. With one 2K image, after 9.04 s.
At the default target of an answer starting within 3 s (720p, one image per camera), it keeps up with 2 cameras at once.
Qwen3.5-4B (4.7B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin, starts answering a single camera that sends one 720p image after 1.57 s, then writes 33.6 tok/s.
With 5 images per camera at 720p, the answer starts after 7.14 s. With one 2K image, after 9.04 s.
At the default target of an answer starting within 3 s (720p, one image per camera), it keeps up with 2 cameras at once.