NVIDIA DGX Spark vs NVIDIA Jetson AGX Thor

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.

No licensed photo available — placeholder drawing.

Split result: NVIDIA DGX Spark is faster in 3 and NVIDIA Jetson AGX Thor in 2 of 5 like-for-like comparisons.

	NVIDIA DGX Spark	NVIDIA Jetson AGX Thor
Best object detection	990 FPS B undated	719 FPS B undated
Power	153 W spec	130 W spec
Perf / W	6.47 FPS/W spec	5.53 FPS/W spec
Price	$4699 list	$3499 list
Workloads with data	2 of 7	2 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.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA DGX Spark	990 FPS inference_time · b=1	YOLO11n FP16 · Ultralytics TensorRT · nano (YOLO-n)	B	153 W spec platform spec envelope (not measured with this result)	Ultralytics docs benchmark table undated
NVIDIA Jetson AGX Thor	719 FPS inference_time · b=1	YOLO26n FP16 · Ultralytics TensorRT · nano (YOLO-n)	B	130 W spec platform spec envelope (not measured with this result)	Ultralytics docs benchmark table undated

instance segmentation

◌

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

semantic segmentation

◌

No published semantic segmentation results for NVIDIA DGX Spark or NVIDIA Jetson AGX Thor 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 Thor 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.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA DGX Spark	60.39 tok/s tg128 · b=1	Llama 2 7B Q4_0 · llama.cpp Vulkan (FA on, commit 657e011) · LLM 5–14B	C	153 W spec platform spec envelope (not measured with this result)	llama.cpp discussion #10879 Vulkan scoreboard (via GitHub API) 2026-10-10
NVIDIA Jetson AGX Thor	45.00 tok/s tok/s gen, concurrency 1 · b=1	Qwen2.5-VL 7B n/s on page · NVIDIA (vLLM/TensorRT-LLM per page) · LLM 5–14B	D	130 W spec platform spec envelope (not measured with this result)	NVIDIA Jetson Benchmarks undated

✓ Like-for-like: model-size class LLM >40B, batch unknown (size or batch not stated by source — unverified). Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA DGX Spark	4.56 tok/s tg · b=unknown	70B-class LLM (Q4) ~Q4 · as reviewed (Ollama/llama.cpp class) · LLM >40B	C	153 W measured reported in result source — measured	vminstall.com review 2026 (year only)
NVIDIA Jetson AGX Thor	4.40 tok/s tg · b=unknown	70B-class LLM (Q4) ~Q4 · as reviewed (Ollama/llama.cpp class) · LLM >40B	C	100 W measured reported in result source — measured	vminstall.com review 2026 (year only)

✓ Like-for-like: model-size class unknown, batch 1 (size or batch not stated by source — unverified). Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA Jetson AGX Thor	117 tok/s generation_throughput · b=1	Pi 0.5 NVFP4 + FP8 · TRT · unknown	C	130 W spec platform spec envelope (not measured with this result)	NVIDIA Jetson AI Lab benchmarks (benchmarks.json) undated
NVIDIA DGX Spark	59.60 tok/s generation_throughput · b=1	Nemotron 3 Nano Omni NVFP4 · vLLM · unknown	C	153 W spec platform spec envelope (not measured with this result)	NVIDIA Jetson AI Lab benchmarks (benchmarks.json) undated

✓ Like-for-like: model-size class unknown, batch 8 (size or batch not stated by source — unverified). Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA Jetson AGX Thor	293 tok/s generation_throughput · b=8	Cosmos3 Edge (Reasoner) BF16 · vLLM · unknown	C	130 W spec platform spec envelope (not measured with this result)	NVIDIA Jetson AI Lab benchmarks (benchmarks.json) undated
NVIDIA DGX Spark	191 tok/s generation_throughput · b=8	Nemotron 3 Nano Omni NVFP4 · vLLM · unknown	C	153 W spec platform spec envelope (not measured with this result)	NVIDIA Jetson AI Lab benchmarks (benchmarks.json) undated

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.