VLM Inference Benchmark Explorer
Qwen3.5-4B on Jetson Orin NX — 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 Orin NX |
| Quantization | Q4_K_M |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (response ≤ 3 s) | 0 |
| Engine | llama.cpp |
| Cameras | Response (s) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 3.72 | 15.6 | FAIL |
| 2 | 5.45 | 10.4 | FAIL |
| 4 | 12.6 | 12.5 | FAIL |
Qwen3.5-4B (4.7B parameters), served in Q4_K_M format with llama.cpp on Jetson Orin NX, starts answering a single camera that sends one 720p image after 3.72 s, then writes 15.6 tok/s.
With 5 images per camera at 720p, the answer starts after 17.25 s. With one 1080p image, after 8.48 s.
At the default target of an answer starting within 3 s (720p, one image per camera), not even one camera is answered in time.
Qwen3.5-4B (4.7B parameters), served in Q4_K_M format with llama.cpp on Jetson Orin NX, starts answering a single camera that sends one 720p image after 3.72 s, then writes 15.6 tok/s.
With 5 images per camera at 720p, the answer starts after 17.25 s. With one 1080p image, after 8.48 s.
At the default target of an answer starting within 3 s (720p, one image per camera), not even one camera is answered in time.