NVIDIA Jetson AGX Thor vs Raspberry Pi 5 (CPU only)

No licensed photo available — placeholder drawing.

Raspberry Pi 5 single-board computer, top view, showing the Broadcom SoC, RAM, USB and Ethernet ports — Raspberry Pi 5. Photo: SimonWaldherr, CC BY 4.0, via Wikimedia Commons.

NVIDIA Jetson AGX Thor is faster in all 3 like-for-like comparisons (largest gap: object detection, 48.22×).

	NVIDIA Jetson AGX Thor	Raspberry Pi 5 (CPU only)
Best object detection	719 FPS B undated	14.92 FPS B undated
Power	130 W spec	n/a
Perf / W	5.53 FPS/W spec	n/a
Price	$3499 list	n/a
Workloads with data	2 of 7	4 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 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
Raspberry Pi 5 (CPU only) CPU-only	14.92 FPS inference_time · b=1	YOLO26n FP32/default · Ultralytics NCNN · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics docs benchmark table undated

instance segmentation

◌

No published instance segmentation results for NVIDIA Jetson AGX Thor or Raspberry Pi 5 (CPU only) 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 AGX Thor or Raspberry Pi 5 (CPU only) 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 Raspberry Pi 5 (CPU only) has published image classification results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Raspberry Pi 5 (CPU only) CPU-only	29.59 FPS inference_time · b=1	YOLO26n-cls FP32 · Ultralytics PyTorch (CPU) · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics docs: Hailo integration benchmark 2026 (year only)

NVIDIA Jetson AGX Thor:

◌

No published image classification results for NVIDIA Jetson AGX Thor or Raspberry Pi 5 (CPU only) 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 Raspberry Pi 5 (CPU only) has published semantic segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Raspberry Pi 5 (CPU only) CPU-only	1.20 FPS inference_time · b=1	YOLO26n-sem FP32 · Ultralytics PyTorch (CPU) · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics docs: Hailo integration benchmark 2026 (year only)

NVIDIA Jetson AGX Thor:

◌

No published semantic segmentation results for NVIDIA Jetson AGX Thor or Raspberry Pi 5 (CPU only) 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 Jetson AGX Thor or Raspberry Pi 5 (CPU only) 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 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
Raspberry Pi 5 (CPU only) CPU-only	1.20 tok/s generation_throughput · b=1	DeepSeek R1 14b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) · LLM 5–14B	C	13.00 W measured reported in result source — measured	Jeff Geerling ai-benchmarks README (Findings tables) undated

✓ Like-for-like: model-size class LLM ≤4B, batch 1. Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
NVIDIA Jetson AGX Thor	122 tok/s generation_throughput · b=1	Qwen3-VL-2B NVFP4 · vLLM · LLM ≤4B	C	130 W spec platform spec envelope (not measured with this result)	NVIDIA Jetson AI Lab benchmarks (benchmarks.json) undated
Raspberry Pi 5 (CPU only) CPU-only	4.88 tok/s generation_throughput · b=1	Llama 3.2:3b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) · LLM ≤4B	C	11.90 W measured reported in result source — measured	Jeff Geerling ai-benchmarks README (Findings tables) 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.