VLM Inference Benchmark Explorer
Gemma-4-E2B-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-E2B-it |
|---|---|
| Parameters | 5.1B |
| Device | Jetson Orin NX 16GB |
| Quantization | Q4_0 |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (TTFT ≤ 3000 ms) | 2 |
| Engine | llama.cpp |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 1379 | 29.8 | ≤3000 ms |
| 2 | 2249 | 28.4 | ≤3000 ms |
| 4 | 4173 | 20.8 | >3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 1379 | 29.8 | ≤3000 ms |
| 3 | 3852 | 29.2 | >3000 ms |
| 5 | 6306 | 29.1 | >3000 ms |
Gemma-4-E2B-it (5.1B 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 1,379 ms (time to first token, TTFT), then writes 29.8 tok/s.
With 5 images per camera at 720p, the answer starts after 6,306 ms. With one 1080p image, after 3,430 ms.
At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), it keeps up with 2 cameras at once.
Gemma-4-E2B-it (5.1B 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 1,379 ms (time to first token, TTFT), then writes 29.8 tok/s.
With 5 images per camera at 720p, the answer starts after 6,306 ms. With one 1080p image, after 3,430 ms.
At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), it keeps up with 2 cameras at once.