Home › Benchmarks › Jetson Orin Nano Super
Benchmark Explorer · Jetson Orin Nano Super
Jetson Orin Nano Super: 63 benchmark rows, 70% measured.
Method v1.4.1 · dataset 2026-09-29 · verified 2026-09-16 · last updated September 2026
44 of 63 rows are measured and published (class C); the rest are EdgeAIStack-derived (class D). 20 model families. Precisions: FP32 (6), FP16 (29), INT8 (20), UNSPECIFIED (8). Runtimes: tensorrt (55), unspecified (8). Tasks: classification (9), detection (42), text generation (4), vision language (4), pose (2), segmentation (2). Jetson Orin Nano Super platform page.
Family × precision: best value
The fastest matching row per family and precision (fps, or tokens/s for language models), with its evidence class. Click a cell for the full breakdown.
| Family | FP32 | FP16 | INT8 | UNSPECIFIED |
|---|---|---|---|---|
| CLIP | — | 314 fps C | — | — |
| DINOv2 | — | 126 fps C | — | — |
| EfficientDet | — | — | 162 fps D | — |
| Gemma 2 | — | — | — | 34.97 tok/s C |
| Llama | — | — | — | 43.07 tok/s C |
| LLaVA | — | — | — | 0.57 tok/s C |
| SSD MobileNet | — | — | 215 fps D | — |
| MobileNetV2 | — | 1176.5 fps C | 1280.4 fps C | — |
| MobileNetV3 | — | 820 fps D | — | — |
| Qwen2.5 | — | — | — | 21.75 tok/s C |
| ResNet | — | 650 fps D | — | — |
| RT-DETR | — | 19.8 fps D | 28.2 fps D | — |
| SmolVLM | — | — | — | 12.9 tok/s C |
| VILA | — | — | — | 1.06 tok/s C |
| ViT | — | 273 fps C | — | — |
| YOLO11 | 134 fps C | 221 fps C | 270 fps C | — |
| YOLO11 | — | 270.7 fps C | — | — |
| YOLO11 | — | 186.1 fps C | — | — |
| YOLO12 | — | 187 fps D | 228.1 fps D | — |
| YOLOv8 | 69.1 fps D | 259 fps C | 341 fps C | — |
Every model on Jetson Orin Nano Super
CLIP Base Patch16
CLIP · base-patch16
CLIP Base Patch32
CLIP · base-patch32
DINOv2 Base Patch14
DINOv2 · base-patch14
EfficientDetd0
EfficientDet · d0
EfficientDetd1
EfficientDet · d1
Gemma 2 Gemma 2 2B It
Gemma 2 · gemma-2-2b-it
Llama 3.1 8B Instruct
Llama · llama-3.1-8b-instruct
Llama 3.2 3B Instruct
Llama · llama-3.2-3b-instruct
LLaVA 1.5 7B Hf
LLaVA · llava-1.5-7b-hf
SSD MobileNetv1
SSD MobileNet · v1
MobileNetV2v2
MobileNetV2 · v2
MobileNetV3 Large
MobileNetV3 · large
Qwen2.5 7B Instruct
Qwen2.5 · qwen2.5-7b-instruct
ResNet50
ResNet · 50
RT-DETRl
RT-DETR · l
RT-DETRx
RT-DETR · x
SmolVLM 2.2B Instruct
SmolVLM · smolvlm-2.2b-instruct
VILA 1.5 3B
VILA · vila-1.5-3b
VILA 1.5 8B
VILA · vila-1.5-8b
ViT Base Patch16
ViT · base-patch16
ViT Base Patch32
ViT · base-patch32
YOLO11l
YOLO11 · l
YOLO11m
YOLO11 · m
YOLO11n
YOLO11 · n
YOLO11s
YOLO11 · s
YOLO11x
YOLO11 · x
YOLO11n
YOLO11 · n
YOLO11s
YOLO11 · s
YOLO11n
YOLO11 · n
YOLO11s
YOLO11 · s
YOLO12l
YOLO12 · l
YOLO12m
YOLO12 · m
YOLO12n
YOLO12 · n
YOLO12s
YOLO12 · s
YOLO12x
YOLO12 · x
YOLOv8l
YOLOv8 · l
YOLOv8m
YOLOv8 · m
YOLOv8n
YOLOv8 · n
YOLOv8s
YOLOv8 · s
YOLOv8x
YOLOv8 · x
Links
- Live engine: https://edgeaistack.ai/engines/benchmark-explorer/?hw=jetson_orin_nano_super&model=clip&variant=base-patch16&mv=1.4.1&dv=2026-09-29
- Methodology: /methodology/benchmark-explorer/
- Dataset: /datasets/benchmarks-v2.json
- Platform page: Jetson Orin Nano Super platform page
- All hardware: /benchmarks/
Query this hardware live.
Filter by model, precision or runtime and get the matching rows with a permanent link.