VLM Inference Benchmark Explorer
Cosmos-Reason2-2B on Jetson AGX Orin 32GB — Q8_0, llama.cpp vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Cosmos-Reason2-2B |
|---|---|
| Parameters | 2.4B |
| Device | Jetson AGX Orin 32GB |
| Quantization | Q8_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 | 1348 | 44.4 | ≤3000 ms |
| 2 | 1827 | 25.8 | ≤3000 ms |
| 4 | 3024 | 17.0 | >3000 ms |
| 8 | 8596 | 21.1 | >3000 ms |
| Images per request | TTFT (ms) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 1348 | 44.4 | ≤3000 ms |
| 3 | 3778 | 43.8 | >3000 ms |
| 5 | 6261 | 41.5 | >3000 ms |
Cosmos-Reason2-2B (2.4B parameters), served in Q8_0 format with llama.cpp on Jetson AGX Orin 32GB, starts answering a single camera that sends one 720p image after 1,348 ms (time to first token, TTFT), then writes 44.4 tok/s.
With 5 images per camera at 720p, the answer starts after 6,261 ms. With one 2K image, after 9,690 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.
Cosmos-Reason2-2B (2.4B parameters), served in Q8_0 format with llama.cpp on Jetson AGX Orin 32GB, starts answering a single camera that sends one 720p image after 1,348 ms (time to first token, TTFT), then writes 44.4 tok/s.
With 5 images per camera at 720p, the answer starts after 6,261 ms. With one 2K image, after 9,690 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.