Apple M4 (10-core GPU, 120 GB/s) vs Dell Pro Max with GB10

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.

Split result: Apple M4 (10-core GPU, 120 GB/s) is faster in 1 and Dell Pro Max with GB10 in 1 of 2 like-for-like comparisons.

	Apple M4 (10-core GPU, 120 GB/s)	Dell Pro Max with GB10
Best LLM generation	41.31 tok/s C undated	97.93 tok/s C undated
Power	30.10 W measured	129 W measured
Perf / W	1.37 tok/s/W measured	0.762 tok/s/W measured
Price	n/a	n/a
Workloads with data	6 of 7	2 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

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

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)
Dell Pro Max with GB10 MIXED: model-size class unknown vs nano (YOLO-n); batch unknown vs 1	78.73 FPS throughput_offline · b=unknown	MLPerf yolo-95 fp4 · CUDA 13.0 · unknown	A	unknown power n/a no power published	MLPerf Inference v6.1 (closed, edge) ID Dell_Pro_Max_GB10x1 undated

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 docs: Apple Core AI integration benchmark 2026 (year only)

Dell Pro Max with GB10:

◌

No published instance segmentation results for Dell Pro Max with GB10 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 docs: Apple Core AI integration benchmark 2026 (year only)

Dell Pro Max with GB10:

◌

No published pose estimation results for Dell Pro Max with GB10 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 docs: Apple Core AI integration benchmark 2026 (year only)

Dell Pro Max with GB10:

◌

No published image classification results for Dell Pro Max with GB10 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.

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 docs: Apple Core AI integration benchmark 2026 (year only)

Dell Pro Max with GB10:

◌

No published semantic segmentation results for Dell Pro Max with GB10 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 Dell Pro Max with GB10 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
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
Dell Pro Max with GB10	23.92 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	138 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
Dell Pro Max with GB10	97.93 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	129 W measured reported in result source — measured	Jeff Geerling ai-benchmarks README (Findings tables) undated
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	C	30.10 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.