HWBench

NVIDIA Jetson Orin NX 16GB vs NVIDIA Jetson Thor T4000

NVIDIA Jetson Orin NX module seated on a carrier motherboard, close-up at Computex 2025
NVIDIA Jetson Orin NX module on a carrier board. Photo: 4300streetcar, CC BY 4.0, via Wikimedia Commons.

NVIDIA Jetson Thor T4000 is faster in all 4 like-for-like comparisons (largest gap: LLM generation, 6.51×).

NVIDIA Jetson Orin NX 16GBNVIDIA Jetson Thor T4000
Best LLM generation65.00 tok/s C
2026-07-21 (page last edited)		423 tok/s C
2026-07-21 (page last edited)
Powern/an/a
Perf / Wn/an/a
Pricen/an/a
Workloads with data4 of 71 of 7

Best published LLM generation 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

Only NVIDIA Jetson Orin NX 16GB has published object detection results.

PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson Orin NX 16GB287 FPS
inference_time · b=1		YOLO26n
INT8 · Ultralytics TensorRT · nano (YOLO-n)		Bunknown power n/a
no power published		Ultralytics documentation (benchmark table)
2026-10-13 (page last edited)

NVIDIA Jetson Thor T4000:

◌

No published object detection results for NVIDIA Jetson Thor T4000 or NVIDIA Jetson Orin NX 16GB yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

instance segmentation

◌

No published instance segmentation results for NVIDIA Jetson Orin NX 16GB or NVIDIA Jetson Thor T4000 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 Jetson Orin NX 16GB or NVIDIA Jetson Thor T4000 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 Orin NX 16GB has published image classification results.

PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson Orin NX 16GB2641 FPS
throughput_offline · b=unknown		MLPerf ResNet
INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN		Dunknown power n/a
no power published		NVIDIA Jetson Benchmarks (MLPerf v3.1 results table)
Older data (2023)

NVIDIA Jetson Thor T4000:

◌

No published image classification results for NVIDIA Jetson Thor T4000 or NVIDIA Jetson Orin NX 16GB 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 Jetson Orin NX 16GB or NVIDIA Jetson Thor T4000 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 Orin NX 16GB has published speech-to-text results.

PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson Orin NX 16GB432 FPS
throughput_offline · b=unknown		MLPerf RNN-T
INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · RNN-T		Dunknown power n/a
no power published		NVIDIA Jetson Benchmarks (MLPerf v3.1 results table)
Older data (2023)

NVIDIA Jetson Thor T4000:

◌

No published speech-to-text results for NVIDIA Jetson Thor T4000 or NVIDIA Jetson Orin NX 16GB 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 Jetson Thor T400035.00 tok/s
generation_throughput · b=1		Qwen 3 8B
NVFP4 · vLLM · LLM 5–14B		Cunknown power n/a
no power published		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
NVIDIA Jetson Orin NX 16GB11.00 tok/s
generation_throughput · b=1		Nemotron Nano 9B V2
W4A16 · vLLM · LLM 5–14B		Cunknown power n/a
no power published		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
✓ Like-for-like: model-size class LLM 5–14B, batch 8. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson Thor T4000200 tok/s
generation_throughput · b=8		Qwen 3 8B
NVFP4 · vLLM · LLM 5–14B		Cunknown power n/a
no power published		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
NVIDIA Jetson Orin NX 16GB60.00 tok/s
generation_throughput · b=8		Nemotron Nano 9B V2
W4A16 · vLLM · LLM 5–14B		Cunknown power n/a
no power published		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
✓ Like-for-like: model-size class LLM ≤4B, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson Thor T400095.00 tok/s
generation_throughput · b=1		Qwen3-VL-2B
NVFP4 · vLLM · LLM ≤4B		Cunknown power n/a
no power published		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
NVIDIA Jetson Orin NX 16GB25.00 tok/s
generation_throughput · b=1		Cosmos Reasoning 2 2B
W4A16 · vLLM · LLM ≤4B		Cunknown power n/a
no power published		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
✓ Like-for-like: model-size class LLM ≤4B, batch 8. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
NVIDIA Jetson Thor T4000423 tok/s
generation_throughput · b=8		Qwen3-VL-2B
NVFP4 · vLLM · LLM ≤4B		Cunknown power n/a
no power published		NVIDIA Jetson AI Lab benchmarks (benchmarks.json)
2026-07-21 (page last edited)
NVIDIA Jetson Orin NX 16GB65.00 tok/s
generation_throughput · b=8		Cosmos Reasoning 2 2B
W4A16 · vLLM · LLM ≤4B		Cunknown power n/a
no power published		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.