Skip to content

Apple M4 (10-core GPU, 120 GB/s) vs Qualcomm Dragonwing RB3 Gen 2 (QCS6490)

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.

Qualcommedge SoC dev kitNo licensed photo yet

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)	Qualcomm Dragonwing RB3 Gen 2 (QCS6490)
Best object detection	357 FPS B 2026-10-01 (page last edited)	276 FPS D 2026-10-07 (published)
Power	n/a	n/a
Perf / W	n/a	n/a
Price	n/a	n/a
Workloads with data	6 of 7	6 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 unknown 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)
Qualcomm Dragonwing RB3 Gen 2 (QCS6490) MIXED: model-size class unknown vs nano (YOLO-n)	276 FPS inference_time · b=1	yolov8_det / YOLOv8-Detection w8a8 · Qualcomm AI Hub tflite (QAIRT 2.50.0.260828221209) · unknown	D	unknown power n/a no power published	Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published)

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

instance segmentation

⚠ 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)	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)
Qualcomm Dragonwing RB3 Gen 2 (QCS6490) MIXED: model-size class unknown vs nano (YOLO-n)	240 FPS inference_time · b=1	yolov8_seg / YOLOv8-Segmentation w8a8 · Qualcomm AI Hub tflite (QAIRT 2.50.0.260828221209) · unknown	D	unknown power n/a no power published	Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published)

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

pose estimation

⚠ 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
Qualcomm Dragonwing RB3 Gen 2 (QCS6490)	291 FPS inference_time · b=1	hrnet_pose w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) · mid-size CNN	D	unknown power n/a no power published	Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published)
Apple M4 (10-core GPU, 120 GB/s) MIXED: model-size class nano (YOLO-n) vs mid-size CNN	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)

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
Qualcomm Dragonwing RB3 Gen 2 (QCS6490)	940 FPS inference_time · b=1	mobilenet_v2 w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) · mobile-class CNN	D	unknown power n/a no power published	Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published)
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 documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)

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

semantic segmentation

⚠ 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
Qualcomm Dragonwing RB3 Gen 2 (QCS6490)	71.69 FPS inference_time · b=1	deeplabv3_plus_mobilenet w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) · mobile-class CNN	D	unknown power n/a no power published	Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published)
Apple M4 (10-core GPU, 120 GB/s) MIXED: model-size class nano (YOLO-n) vs mobile-class 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 documentation: Apple Core AI integration benchmark 2026-10-01 (page last edited)

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

speech-to-text

Only Qualcomm Dragonwing RB3 Gen 2 (QCS6490) has published speech-to-text results.

Platform	Result	Model · precision · stack	Grade	Power	Source
Qualcomm Dragonwing RB3 Gen 2 (QCS6490)	42.65 FPS inference_time · b=1	whisper_small_quantized / decoder w8a16 · Qualcomm AI Hub voice_ai (QAIRT 2.50.0.260828221209) · Whisper small	D	unknown power n/a no power published	Qualcomm AI Hub Models perf.yaml (BSD-3) 2026-10-07 (published)

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

◌

No published speech-to-text results for Apple M4 (10-core GPU, 120 GB/s) or Qualcomm Dragonwing RB3 Gen 2 (QCS6490) 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)

Qualcomm Dragonwing RB3 Gen 2 (QCS6490):

◌

No published LLM generation results for Qualcomm Dragonwing RB3 Gen 2 (QCS6490) 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.