VLM Inference Benchmark Explorer
Gemma-4-E4B-it on Jetson Orin NX 16GB — Q4_0, llama.cpp vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Gemma-4-E4B-it |
|---|---|
| Parameters | 8.0B |
| Device | Jetson Orin NX 16GB |
| Quantization | Q4_0 |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (TTFT ≤ 3000 ms) | 1 |
| Engine | llama.cpp |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 1856 | 17.2 | ≤3000 ms |
| 2 | 3060 | 12.3 | >3000 ms |
| 4 | 6032 | 12.8 | >3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 1856 | 17.2 | ≤3000 ms |
| 3 | 5075 | 16.9 | >3000 ms |
| 5 | 8315 | 16.8 | >3000 ms |
Gemma-4-E4B-it (8.0B parameters), served in Q4_0 format with llama.cpp on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 1,856 ms (time to first token, TTFT), then writes 17.2 tok/s.
With 5 images per camera at 720p, the answer starts after 8,315 ms. With one 1080p image, after 4,451 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.
Gemma-4-E4B-it (8.0B parameters), served in Q4_0 format with llama.cpp on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 1,856 ms (time to first token, TTFT), then writes 17.2 tok/s.
With 5 images per camera at 720p, the answer starts after 8,315 ms. With one 1080p image, after 4,451 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.