HWBench

NVIDIA DGX Spark vs NVIDIA Jetson AGX Orin 64GB

NVIDIA DGX Spark desktop AI computer, gold metal-foam chassis, oblique view on a wooden table
NVIDIA DGX Spark. Photo: Daniel Lu (User:dllu), CC BY-SA 4.0, via Wikimedia Commons.
NVIDIA Jetson AGX Orin developer kit with its retail box, on a black background
NVIDIA Jetson AGX Orin developer kit. Photo: Auledas, CC BY 4.0, via Wikimedia Commons.
Showing the newest results per platform and source. 12 superseded older results are hidden.Showing all results, including 12 superseded by newer results from the same source.

NVIDIA DGX Spark is faster in all 4 like-for-like comparisons (largest gap: object detection, 2.28×).

NVIDIA DGX SparkNVIDIA Jetson AGX Orin 64GB
Best object detection990 FPS B
2026-09-27 (page last edited)		435 FPS B
2026-10-13 (page last edited)
Power153 W spec65.00 W spec
Perf / W6.47 FPS/W spec6.69 FPS/W spec
Price$6950 list$3499 list
Workloads with data2 of 73 of 7

Best published object detection result per platform (may be from different like-for-like groups — see data). n/a = not published; never estimated.

Show data — all workloads, sources and like-for-like groups

object detection

✓ Like-for-like: model-size class nano (YOLO-n), batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA DGX Spark990 FPS
inference_time · b=1		YOLO11n
FP16 · Ultralytics TensorRT · nano (YOLO-n)		B153 W spec
platform spec envelope (not measured with this result)		Ultralytics documentation (benchmark table)
2026-09-27 (page last edited)
NVIDIA Jetson AGX Orin 64GB435 FPS
inference_time · b=1		YOLO26n
INT8 · Ultralytics TensorRT · nano (YOLO-n)		B65.00 W spec
platform spec envelope (not measured with this result)		Ultralytics documentation (benchmark table)
2026-10-13 (page last edited)

instance segmentation

◌

No published instance segmentation results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

◌

No published pose estimation results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

image classification

◌

No published image classification results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

semantic segmentation

Only NVIDIA Jetson AGX Orin 64GB has published semantic segmentation results.

PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson AGX Orin 64GB104 FPS
throughput · b=1		SegFormer-B0 (640x640)
FP16 · TensorRT (ONNX export) · unknown		C65.00 W spec
platform spec envelope (not measured with this result)		arXiv 2608.00927 AgriJetsonBench (abstract figures)
2026-08-02 (published)

NVIDIA DGX Spark:

◌

No published semantic segmentation results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

speech-to-text

◌

No published speech-to-text results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

✓ Like-for-like: model-size class LLM 5–14B, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA DGX Spark60.39 tok/s
tg128 · b=1		Llama 2 7B
Q4_0 · llama.cpp Vulkan (FA on, commit 657e011) · LLM 5–14B		C153 W spec
platform spec envelope (not measured with this result)		llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API)
2026-10-10 (page last edited)
NVIDIA Jetson AGX Orin 64GB30.00 tok/s
generation_throughput · b=1		Qwen 3 8B
W4A16 · vLLM · LLM 5–14B		C65.00 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
✓ Like-for-like: model-size class unknown, batch 1 (size or batch not stated by source — unverified). Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA DGX Spark59.60 tok/s
generation_throughput · b=1		Nemotron 3 Nano Omni
NVFP4 · vLLM · unknown		C153 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
NVIDIA Jetson AGX Orin 64GB44.00 tok/s
generation_throughput · b=1		Cosmos3 Edge (Reasoner)
BF16 · vLLM · unknown		C65.00 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
✓ Like-for-like: model-size class unknown, batch 8 (size or batch not stated by source — unverified). Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA DGX Spark191 tok/s
generation_throughput · b=8		Nemotron 3 Nano Omni
NVFP4 · vLLM · unknown		C153 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
NVIDIA Jetson AGX Orin 64GB171 tok/s
generation_throughput · b=8		Cosmos3 Edge (Reasoner)
BF16 · vLLM · unknown		C65.00 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)

NVIDIA DGX Spark is faster in all 4 like-for-like comparisons (largest gap: object detection, 2.28×).

NVIDIA DGX SparkNVIDIA Jetson AGX Orin 64GB
Best object detection990 FPS B
2026-09-27 (page last edited)		435 FPS B
2026-10-13 (page last edited)
Power153 W spec65.00 W spec
Perf / W6.47 FPS/W spec6.69 FPS/W spec
Price$6950 list$3499 list
Workloads with data2 of 75 of 7

Best published object detection result per platform (may be from different like-for-like groups — see data). n/a = not published; never estimated.

Show data — all workloads, sources and like-for-like groups

object detection

✓ Like-for-like: model-size class nano (YOLO-n), batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA DGX Spark990 FPS
inference_time · b=1		YOLO11n
FP16 · Ultralytics TensorRT · nano (YOLO-n)		B153 W spec
platform spec envelope (not measured with this result)		Ultralytics documentation (benchmark table)
2026-09-27 (page last edited)
NVIDIA Jetson AGX Orin 64GB435 FPS
inference_time · b=1		YOLO26n
INT8 · Ultralytics TensorRT · nano (YOLO-n)		B65.00 W spec
platform spec envelope (not measured with this result)		Ultralytics documentation (benchmark table)
2026-10-13 (page last edited)

instance segmentation

◌

No published instance segmentation results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

◌

No published pose estimation results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

image classification

Only NVIDIA Jetson AGX Orin 64GB has published image classification results.

PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson AGX Orin 64GB6424 FPS
throughput_offline · b=unknown		MLPerf ResNet
INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN		D65.00 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson Benchmarks (MLPerf v3.1 results table)
Older data (2023)

NVIDIA DGX Spark:

◌

No published image classification results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

semantic segmentation

Only NVIDIA Jetson AGX Orin 64GB has published semantic segmentation results.

PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson AGX Orin 64GB104 FPS
throughput · b=1		SegFormer-B0 (640x640)
FP16 · TensorRT (ONNX export) · unknown		C65.00 W spec
platform spec envelope (not measured with this result)		arXiv 2608.00927 AgriJetsonBench (abstract figures)
2026-08-02 (published)

NVIDIA DGX Spark:

◌

No published semantic segmentation results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

speech-to-text

Only NVIDIA Jetson AGX Orin 64GB has published speech-to-text results.

PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson AGX Orin 64GB1170 FPS
throughput_offline · b=unknown		MLPerf RNN-T
INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · RNN-T		D65.00 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson Benchmarks (MLPerf v3.1 results table)
Older data (2023)

NVIDIA DGX Spark:

◌

No published speech-to-text results for NVIDIA DGX Spark or NVIDIA Jetson AGX Orin 64GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

✓ Like-for-like: model-size class LLM 5–14B, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA DGX Spark60.39 tok/s
tg128 · b=1		Llama 2 7B
Q4_0 · llama.cpp Vulkan (FA on, commit 657e011) · LLM 5–14B		C153 W spec
platform spec envelope (not measured with this result)		llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API)
2026-10-10 (page last edited)
NVIDIA Jetson AGX Orin 64GB30.00 tok/s
generation_throughput · b=1		Qwen 3 8B
W4A16 · vLLM · LLM 5–14B		C65.00 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
✓ Like-for-like: model-size class unknown, batch 1 (size or batch not stated by source — unverified). Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA DGX Spark59.60 tok/s
generation_throughput · b=1		Nemotron 3 Nano Omni
NVFP4 · vLLM · unknown		C153 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
NVIDIA Jetson AGX Orin 64GB44.00 tok/s
generation_throughput · b=1		Cosmos3 Edge (Reasoner)
BF16 · vLLM · unknown		C65.00 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
✓ Like-for-like: model-size class unknown, batch 8 (size or batch not stated by source — unverified). Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA DGX Spark191 tok/s
generation_throughput · b=8		Nemotron 3 Nano Omni
NVFP4 · vLLM · unknown		C153 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
NVIDIA Jetson AGX Orin 64GB171 tok/s
generation_throughput · b=8		Cosmos3 Edge (Reasoner)
BF16 · vLLM · unknown		C65.00 W spec
platform spec envelope (not measured with this result)		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
How to read these numbers
Every number is labelled. Confidence: A MLPerf closed, audited · B documented third-party method · C community / review · D vendor-published, not independently verified · E estimate. Power basis: measured with the result · spec vendor spec/envelope · power n/a not published.

Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.