HWBench

Apple M4 (10-core GPU, 120 GB/s) vs Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling)

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.
Showing the newest results per platform and source. 6 superseded older results are hidden.Showing all results, including 6 superseded by newer results from the same source.

Apple M4 (10-core GPU, 120 GB/s) is faster in all 2 like-for-like comparisons (largest gap: LLM generation, 6.17×).

Apple M4 (10-core GPU, 120 GB/s)Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling)
Best LLM generation41.31 tok/s C
2026-09-22 (page last edited)		17.99 tok/s C
Older data (2025)
Power30.10 W ● Measured, Whole system29.90 W ● Measured, Whole system
Perf / W1.37 tok/s/W ● Measured, Whole system0.602 tok/s/W ● Measured, Whole system
Pricen/an/a
Workloads with data6 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 Apple M4 (10-core GPU, 120 GB/s) has published object detection results.

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published object detection results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published instance segmentation results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published pose estimation results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published image classification results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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

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

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published semantic segmentation results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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.

speech-to-text

◌

No published speech-to-text results for Apple M4 (10-core GPU, 120 GB/s) or Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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
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		Cunknown power not published
not published		llama.cpp discussion #4167 scoreboard (via GitHub API)
2026-10-01 (page last edited)
Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling)3.91 tok/s
generation_throughput · b=1		llama3.1:8b
Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM 5–14B		C29.80 W ● Measured, Whole system
reported in result source — Measured, Whole system		Jeff Geerling ai-benchmarks issue results (comments)
Older data (2025)
✓ Like-for-like: model-size class LLM ≤4B, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Apple M4 (10-core GPU, 120 GB/s)41.31 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		C30.10 W ● Measured, Whole system
reported in result source — Measured, Whole system		Jeff Geerling ai-benchmarks README (Findings tables)
2026-09-22 (page last edited)
Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling)17.99 tok/s
generation_throughput · b=1		deepseek-r1:1.5b
Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM ≤4B		C29.90 W ● Measured, Whole system
reported in result source — Measured, Whole system		Jeff Geerling ai-benchmarks issue results (comments)
Older data (2025)

Apple M4 (10-core GPU, 120 GB/s) is faster in all 2 like-for-like comparisons (largest gap: LLM generation, 6.17×).

Apple M4 (10-core GPU, 120 GB/s)Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling)
Best LLM generation41.31 tok/s C
2026-09-22 (page last edited)		17.99 tok/s C
Older data (2025)
Power30.10 W ● Measured, Whole system29.90 W ● Measured, Whole system
Perf / W1.37 tok/s/W ● Measured, Whole system0.602 tok/s/W ● Measured, Whole system
Pricen/an/a
Workloads with data6 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 Apple M4 (10-core GPU, 120 GB/s) has published object detection results.

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published object detection results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published instance segmentation results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published pose estimation results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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.

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published image classification results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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

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

PlatformResultModel · precision · stackGradePowerSource
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)		B65.00 W Board TDP, Whole system
reported in result source — Board TDP, Whole system		Ultralytics documentation: Apple Core AI integration benchmark
2026-10-01 (page last edited)

Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling):

◌

No published semantic segmentation results for Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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.

speech-to-text

◌

No published speech-to-text results for Apple M4 (10-core GPU, 120 GB/s) or Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling) 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
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		Cunknown power not published
not published		llama.cpp discussion #4167 scoreboard (via GitHub API)
2026-10-01 (page last edited)
Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling)3.91 tok/s
generation_throughput · b=1		llama3.1:8b
Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM 5–14B		C29.80 W ● Measured, Whole system
reported in result source — Measured, Whole system		Jeff Geerling ai-benchmarks issue results (comments)
Older data (2025)
✓ Like-for-like: model-size class LLM ≤4B, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Apple M4 (10-core GPU, 120 GB/s)41.31 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		C30.10 W ● Measured, Whole system
reported in result source — Measured, Whole system		Jeff Geerling ai-benchmarks README (Findings tables)
2026-09-22 (page last edited)
Intel N150 Mini PC (GMKTek G3 Plus) (as tested by Jeff Geerling)17.99 tok/s
generation_throughput · b=1		deepseek-r1:1.5b
Ollama default tag (4-bit unless tag says otherwise) · Ollama (geerlingguy/ollama-benchmark) · LLM ≤4B		C29.90 W ● Measured, Whole system
reported in result source — Measured, Whole system		Jeff Geerling ai-benchmarks issue results (comments)
Older data (2025)

Grades: A audited MLPerf · B third-party · C community · D vendor. How we rank · JSON