VLM Inference Benchmark Explorer
Qwen3.6-27B on Jetson AGX Orin 32GB Developer Kit — Q4_K_M, llama.cpp vision-language inference benchmark
Open this configuration in the VLM Inference Benchmark Explorer
| Model | Qwen3.6-27B |
|---|---|
| Parameters | 27B |
| Device | Jetson AGX Orin 32GB Developer Kit |
| Quantization | Q4_K_M |
| Image size | 720p |
| Images per camera | 1 |
| Max Cameras (response ≤ 3 s) | >3 s |
| Engine | llama.cpp |
| Cameras | Response (s) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 5.68 | 7.3 | >3 s |
| 2 | 11.3 | 6.5 | >3 s |
| 4 | 21.1 | 5.1 | >3 s |
| 8 | 60.8 | 5.3 | >3 s |
| Images per request | Response (s) | TPS (tok/s) | Target |
|---|---|---|---|
| 1 | 5.68 | 7.3 | >3 s |
| 2 | 11.0 | 7.2 | >3 s |
| 4 | 21.6 | 7.1 | >3 s |
| 8 | 42.9 | 7.0 | >3 s |
| 16 | 86.7 | 6.6 | >3 s |
| 32 | 184.3 | 6.1 | >3 s |
Qwen3.6-27B (27B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin 32GB Developer Kit, starts answering a single camera that sends one 720p image after 5.68 s, then writes 7.3 tok/s.
With 32 images per camera at 720p, the answer starts after 184.29 s. With one 1080p image, after 14.11 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.
Qwen3.6-27B (27B parameters), served in Q4_K_M format with llama.cpp on Jetson AGX Orin 32GB Developer Kit, starts answering a single camera that sends one 720p image after 5.68 s, then writes 7.3 tok/s.
With 32 images per camera at 720p, the answer starts after 184.29 s. With one 1080p image, after 14.11 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.