HWBenchedge-AI hardware data, cited & graded

Apple M4 Max (40-core GPU, 546 GB/s): edge AI benchmarks

Applelaptop/desktop SoC · no photo yet
No licensed photo available — placeholder drawing.
Vendor AppleForm factor laptop/desktop SoCCompute GPUIndicative price unknownPower envelope unknownPublished rows 4
LLM generation83.06 tok/sC perf/W n/a2026-10-01

Best published result per workload, across model sizes — open “Show data” for like-for-like groups.

Show data — per-workload tables

object detection

◌

No published object detection results for Apple M4 Max (40-core GPU, 546 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

◌

No published instance segmentation results for Apple M4 Max (40-core GPU, 546 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

◌

No published pose estimation results for Apple M4 Max (40-core GPU, 546 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

◌

No published image classification results for Apple M4 Max (40-core GPU, 546 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

◌

No published semantic segmentation results for Apple M4 Max (40-core GPU, 546 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 Max (40-core GPU, 546 GB/s) 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 groupBest resultModel · precision · stackGradePowerSource · dateRank in group
LLM 5–14B · b=183.06 tok/sLlama 2 7B
Q4_0 · llama.cpp Metal (commit 8e672ef)
Cunknown power n/allama.cpp discussion #4167 scoreboard (via GitHub API)
2026-10-01
8 of 53
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.