Apple M4 (10-core GPU, 120 GB/s) vs Hailo-8L (M.2/PCIe, x86 host)

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.

No licensed photo available — placeholder drawing.

Apple M4 (10-core GPU, 120 GB/s) is faster in all 2 like-for-like comparisons (largest gap: object detection, 1.78×).

	Apple M4 (10-core GPU, 120 GB/s)	Hailo-8L (M.2/PCIe, x86 host)
Best object detection	357 FPS B 2026 (year only)	437 FPS D undated
Power	n/a	1.50 W spec
Perf / W	n/a	291 FPS/W spec
Price	n/a	n/a
Workloads with data	6 of 7	6 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
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 docs: Apple Core AI integration benchmark 2026 (year only)
Hailo-8L (M.2/PCIe, x86 host)	201 FPS throughput · b=1	yolov8n INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n)	D	1.50 W spec reported in result source — spec	Hailo Model Zoo public models (Hailo-8L) undated

instance segmentation

✓ 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
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 docs: Apple Core AI integration benchmark 2026 (year only)
Hailo-8L (M.2/PCIe, x86 host)	168 FPS throughput · b=1	yolov8n_seg INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n)	D	1.50 W spec reported in result source — spec	Hailo Model Zoo public models (Hailo-8L) undated

pose estimation

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

Platform	Result	Model · precision · stack	Grade	Power	Source
Hailo-8L (M.2/PCIe, x86 host)	48.50 FPS throughput · b=1	yolov8m_pose INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m)	D	1.50 W spec reported in result source — spec	Hailo Model Zoo public models (Hailo-8L) undated
Apple M4 (10-core GPU, 120 GB/s) MIXED: model-size class nano (YOLO-n) vs medium (YOLO-m)	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 docs: Apple Core AI integration benchmark 2026 (year only)

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

image classification

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

Platform	Result	Model · precision · stack	Grade	Power	Source
Hailo-8L (M.2/PCIe, x86 host)	1738 FPS throughput · b=1	mobilenet_v2_1.0 INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mobile-class CNN	D	1.50 W spec reported in result source — spec	Hailo Model Zoo public models (Hailo-8L) undated
Apple M4 (10-core GPU, 120 GB/s) MIXED: model-size class nano (YOLO-n) vs mobile-class CNN	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 docs: Apple Core AI integration benchmark 2026 (year only)

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

semantic segmentation

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

Platform	Result	Model · precision · stack	Grade	Power	Source
Hailo-8L (M.2/PCIe, x86 host)	19.60 FPS throughput · b=1	fcn8_resnet_v1_18 INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mid-size CNN	D	1.50 W spec reported in result source — spec	Hailo Model Zoo public models (Hailo-8L) undated
Apple M4 (10-core GPU, 120 GB/s) MIXED: model-size class nano (YOLO-n) vs mid-size CNN	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 docs: Apple Core AI integration benchmark 2026 (year only)

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

speech-to-text

Only Hailo-8L (M.2/PCIe, x86 host) has published speech-to-text results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Hailo-8L (M.2/PCIe, x86 host)	41.80 FPS throughput · b=1	whisper_base_5s_no_kqs_decoder INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · Whisper base	D	1.50 W spec reported in result source — spec	Hailo Model Zoo public models (Hailo-8L) undated

Apple M4 (10-core GPU, 120 GB/s):

◌

No published speech-to-text results for Apple M4 (10-core GPU, 120 GB/s) or Hailo-8L (M.2/PCIe, x86 host) 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

Hailo-8L (M.2/PCIe, x86 host):

◌

No published LLM generation results for Hailo-8L (M.2/PCIe, x86 host) 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.

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.