Apple M4 (10-core GPU, 120 GB/s) vs Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0

Apple Mac mini (M4, 2024), small silver aluminium desktop, front view — Apple Mac mini (M4, 2024) — the M4 Pro model shares this enclosure. Photo: Seasider53, CC BY 4.0, via Wikimedia Commons.

GoogleAI accelerator (USB)No licensed photo yet

Showing the newest results per platform and source. 18 superseded older results are hidden.Showing all results, including 18 superseded by newer results from the same source.

No like-for-like comparison yet: both have published results, but model size or batch differ. Treat the numbers below as indicative only.

	Apple M4 (10-core GPU, 120 GB/s)	Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0
Best semantic segmentation	53.48 FPS B 2026-10-01 (page last edited)	303 FPS D Older data (2020)
Power	n/a	2.00 W spec
Perf / W	n/a	152 FPS/W spec
Price	n/a	n/a
Workloads with data	6 of 7	1 of 7

Best published semantic segmentation result per platform. n/a = not published; never estimated.

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

object detection

Only Apple M4 (10-core GPU, 120 GB/s) has published object detection results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	357 FPS latency_e2e · b=1	YOLO26n FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)

Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0:

◌

No published object detection results for Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 or Apple M4 (10-core GPU, 120 GB/s) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

instance segmentation

Only Apple M4 (10-core GPU, 120 GB/s) has published instance segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	196 FPS latency_e2e · b=1	YOLO26n-seg FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)

Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0:

◌

No published instance segmentation results for Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 or Apple M4 (10-core GPU, 120 GB/s) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

Only Apple M4 (10-core GPU, 120 GB/s) has published pose estimation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	370 FPS latency_e2e · b=1	YOLO26n-pose FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)

Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0:

◌

No published pose estimation results for Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 or Apple M4 (10-core GPU, 120 GB/s) 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 Apple M4 (10-core GPU, 120 GB/s) has published image classification results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	417 FPS latency_e2e · b=1	YOLO26n-cls FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)

Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0:

◌

No published image classification results for Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 or Apple M4 (10-core GPU, 120 GB/s) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

semantic segmentation

⚠ MIXED COMPARISON — not like-for-like. Baseline nano (YOLO-n) at batch 1. Differs: model-size class mid-size CNN vs nano (YOLO-n).

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	53.48 FPS latency_e2e · b=1	YOLO26n-sem FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)
Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 MIXED: model-size class mid-size CNN vs nano (YOLO-n)	303 FPS inference_time · b=1	Unet Mv2 (128x128) INT8 · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mid-size CNN	D	2.00 W spec platform spec envelope (not measured with this result)	Google Coral Edge TPU benchmarks page (Table 1) Older data (2020)

No shared like-for-like group exists for this pair.

speech-to-text

◌

No published speech-to-text results for Apple M4 (10-core GPU, 120 GB/s) or Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

Only Apple M4 (10-core GPU, 120 GB/s) has published LLM generation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	24.11 tok/s tg128 · b=1	Llama 2 7B Q4_0 · llama.cpp Metal (commit 8e672ef) · LLM 5–14B	C	unknown power n/a no power published	llama.cpp discussion #4167 scoreboard (via GitHub API) 2026-10-01 (page last edited)

Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0:

◌

No published LLM generation results for Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 or Apple M4 (10-core GPU, 120 GB/s) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

No like-for-like comparison yet: both have published results, but model size or batch differ. Treat the numbers below as indicative only.

	Apple M4 (10-core GPU, 120 GB/s)	Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0
Best object detection	357 FPS B 2026-10-01 (page last edited)	154 FPS D Older data (2019)
Power	n/a	2.00 W spec
Perf / W	n/a	76.92 FPS/W spec
Price	n/a	n/a
Workloads with data	6 of 7	3 of 7

Best published object detection result per platform. n/a = not published; never estimated.

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

object detection

⚠ MIXED COMPARISON — not like-for-like. Baseline nano (YOLO-n) at batch 1. Differs: model-size class mobile-class CNN vs nano (YOLO-n).

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	357 FPS latency_e2e · b=1	YOLO26n FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)
Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 MIXED: model-size class mobile-class CNN vs nano (YOLO-n)	154 FPS inference_time · b=1	MobileNet v1 SSD (224x224) INT8 · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mobile-class CNN	D	2.00 W spec platform spec envelope (not measured with this result)	Google Coral Edge TPU benchmarks page (Table 1) Older data (2019)

No shared like-for-like group exists for this pair.

instance segmentation

Only Apple M4 (10-core GPU, 120 GB/s) has published instance segmentation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	196 FPS latency_e2e · b=1	YOLO26n-seg FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)

Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0:

◌

pose estimation

Only Apple M4 (10-core GPU, 120 GB/s) has published pose estimation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	370 FPS latency_e2e · b=1	YOLO26n-pose FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)

Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0:

◌

image classification

⚠ MIXED COMPARISON — not like-for-like. Baseline nano (YOLO-n) at batch 1. Differs: model-size class unknown vs nano (YOLO-n).

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	417 FPS latency_e2e · b=1	YOLO26n-cls FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)
Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 MIXED: model-size class unknown vs nano (YOLO-n)	476 FPS inference_time · b=1	SqueezeNet (224x224) INT8 · TensorFlow Lite C++ benchmark (Edge TPU runtime) · unknown	D	2.00 W spec platform spec envelope (not measured with this result)	Google Coral Edge TPU benchmarks page (Table 1) Older data (2019)

No shared like-for-like group exists for this pair.

semantic segmentation

⚠ MIXED COMPARISON — not like-for-like. Baseline nano (YOLO-n) at batch 1. Differs: model-size class mid-size CNN vs nano (YOLO-n).

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	53.48 FPS latency_e2e · b=1	YOLO26n-sem FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 · nano (YOLO-n)	B	unknown power n/a no power published	Ultralytics documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)
Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0 MIXED: model-size class mid-size CNN vs nano (YOLO-n)	303 FPS inference_time · b=1	Unet Mv2 (128x128) INT8 · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mid-size CNN	D	2.00 W spec platform spec envelope (not measured with this result)	Google Coral Edge TPU benchmarks page (Table 1) Older data (2020)

No shared like-for-like group exists for this pair.

speech-to-text

◌

LLM generation

Only Apple M4 (10-core GPU, 120 GB/s) has published LLM generation results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Apple M4 (10-core GPU, 120 GB/s)	24.11 tok/s tg128 · b=1	Llama 2 7B Q4_0 · llama.cpp Metal (commit 8e672ef) · LLM 5–14B	C	unknown power n/a no power published	llama.cpp discussion #4167 scoreboard (via GitHub API) 2026-10-01 (page last edited)

Google Coral USB Accelerator (Edge TPU) on Xeon Gold 6154 host, USB 3.0:

◌

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.