VLM Inference Benchmark Explorer
Cosmos-Reason2-8B on Jetson Orin NX 16GB — Q4_K_M, llama.cpp vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Cosmos-Reason2-8B |
|---|---|
| Parameters | 8.8B |
| Device | Jetson Orin NX 16GB |
| Quantization | Q4_K_M |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (TTFT ≤ 3000 ms) | >3000 ms |
| Engine | llama.cpp |
| Cameras | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 6872 | 11.6 | >3000 ms |
| 2 | 7977 | 6.1 | >3000 ms |
| 4 | 15528 | 5.4 | >3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 6872 | 11.6 | >3000 ms |
| 3 | 20421 | 11.1 | >3000 ms |
| 5 | 34194 | 10.7 | >3000 ms |
Cosmos-Reason2-8B (8.8B parameters), served in Q4_K_M format with llama.cpp on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 6,872 ms (time to first token, TTFT), then writes 11.6 tok/s.
With 5 images per camera at 720p, the answer starts after 34,194 ms. With one 1080p image, after 21,752 ms.
At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), not even one camera is answered in time.
Cosmos-Reason2-8B (8.8B parameters), served in Q4_K_M format with llama.cpp on Jetson Orin NX 16GB, starts answering a single camera that sends one 720p image after 6,872 ms (time to first token, TTFT), then writes 11.6 tok/s.
With 5 images per camera at 720p, the answer starts after 34,194 ms. With one 1080p image, after 21,752 ms.
At the default target of a mean TTFT within 3,000 ms (720p, one image per camera), not even one camera is answered in time.