Features Models Benchmark Ranking FAQ

MLXHub · Benchmark v1

Device ranking

Global score in Benchmark v1. 1000 = iPad Pro 12.9″ (M1) with 8 GB, so a score of 1570 means about 1.57 times the performance of that reference.

  • Data updated October 11, 2026
  • Devices ranked: 2
  • Best result per device model and memory
  • What does 1000 mean?
Global score, scale from 0 iPad Pro 12.9″ (M1), 8 GB = 1,000
  1. Profile compared with the reference

    Each metric as a multiple of the iPad Pro 12.9″ (M1), 8 GB. Bars start at 0; the line marks 1×.

    • Generation 1.39×
    • Usable memory 0.75×
    • Cold prompt processing 5.20×
    • Endurance 1.06×
    • Expert reading 2.61×
    • Model loading 2.18×

    Below the reference: usable memory, 4.39 GB compared with 5.84 GB on the M1.

    Score by category

    4-bit models
    1,352.91
    8-bit models
    1,654.93

    Generation speed

    44.5 tok/s

    Gemma 4 E2B 4-bit · M1: 36.6 tok/s

    Usable memory

    4.39 GB

    M1: 5.84 GB

    Measured with

    iOS 27.0 · MLXHub 2.2.1

    Measured on Sep 16, 2026

    Under the hood

    Tokens per second while each scenario generates, about one sample per second, with the device's thermal state behind. Breaks in the line are model loading and prompt processing.

    Gemma 4 E2B4-bitNominal
    60 30 0 s 480 s

    Average 43.5 tok/sBattery −5 %

    Gemma 4 E4B4-bitFair
    30 15 0 s 480 s

    Average 22.1 tok/sBattery −5 %

    Gemma 4 E2B8-bitNominal
    30 15 0 s 480 s

    Average 24.8 tok/sBattery −5 %

    LFM2.5 8B A1B8-bitExperts from storageSerious
    10 5 0 s 480 s

    Average 5.2 tok/sBattery −10 %83 s serious or worse

    Every scenario, as measured
    ScenarioPrompt tokensGeneratedPrefill tok/sDecode tok/sLoad GB/sEnduranceStorage MB/s
    Gemma 4 E2B 4-bit short4215,696917.444.52.270.963—
    Gemma 4 E2B 4-bit long4,5413,2323,307.241.82.070.982—
    Gemma 4 E4B 4-bit short4212,624426.222.12.170.927—
    Gemma 4 E4B 4-bit long4,5411,056933.221.93.111.000—
    Gemma 4 E2B 8-bit short4213,872257.424.93.250.981—
    Gemma 4 E2B 8-bit long4,5412,4323,299.324.43.250.994—
    LFM2.5 8B A1B 8-bit short42160866.65.19.730.9373,397
    LFM2.5 8B A1B 8-bit long4,5419683.45.19.620.7763,016

    Memory test

    Usable memory
    4.39 GB
    Peak footprint
    5.17 GB
    Physical memory
    12.3 GB
    Test duration
    19 s
    Stopped at
    Critical memory warning

    Run

    Total duration
    38.8 min
    CPU cores
    6
    OS build
    24A437
    App build
    84
    Battery
    80 % → 55 %
    Low Power Mode
    No
    Charging
    No
    Peak thermal state
    Serious
  2. Profile compared with the reference

    Each metric as a multiple of the iPad Pro 12.9″ (M1), 8 GB. Bars start at 0; the line marks 1×.

    • Generation 1.00×
    • Usable memory 1.00×
    • Cold prompt processing 1.00×
    • Endurance 1.00×
    • Expert reading 1.00×
    • Model loading 1.00×

    This is the reference device, so every metric is exactly 1×.

    Score by category

    4-bit models
    1,000.00
    8-bit models
    1,000.00

    Generation speed

    36.6 tok/s

    Gemma 4 E2B 4-bit · M1: 36.6 tok/s

    Usable memory

    5.84 GB

    M1: 5.84 GB

    Measured with

    iPadOS 27.0 · MLXHub 2.2.1

    Measured on Sep 16, 2026

    Under the hood

    Tokens per second while each scenario generates, about one sample per second, with the device's thermal state behind. Breaks in the line are model loading and prompt processing.

    Gemma 4 E2B4-bitNominal
    50 25 0 s 480 s

    Average 35.5 tok/sBattery −5 %

    Gemma 4 E4B4-bitNominal
    30 15 0 s 480 s

    Average 18.7 tok/sBattery −5 %

    Gemma 4 E2B8-bitSerious
    30 15 0 s 480 s

    Average 15.4 tok/sBattery −10 %210 s serious or worse

    LFM2.5 8B A1B8-bitExperts from storageSerious
    10 5 0 s 480 s

    Average 3.7 tok/sBattery −10 %177 s serious or worse

    Every scenario, as measured
    ScenarioPrompt tokensGeneratedPrefill tok/sDecode tok/sLoad GB/sEnduranceStorage MB/s
    Gemma 4 E2B 4-bit short4212,304207.936.61.210.965—
    Gemma 4 E2B 4-bit long4,541928671.332.41.181.000—
    Gemma 4 E4B 4-bit short42192873.818.81.010.961—
    Gemma 4 E4B 4-bit long4,541224162.718.21.091.000—
    Gemma 4 E2B 8-bit short42192815.413.50.990.786—
    Gemma 4 E2B 8-bit long4,541544243.613.01.110.676—
    LFM2.5 8B A1B 8-bit short42128833.13.75.651.0001,106
    LFM2.5 8B A1B 8-bit long4,5416451.73.96.370.7711,366

    Memory test

    Usable memory
    5.84 GB
    Peak footprint
    6.87 GB
    Physical memory
    7.9 GB
    Test duration
    92 s
    Stopped at
    Critical memory warning

    Run

    Total duration
    48.2 min
    CPU cores
    8
    OS build
    24A435
    App build
    84
    Battery
    65 % → 35 %
    Low Power Mode
    No
    Charging
    No
    Peak thermal state
    Serious

Only a few devices have been published so far. Run the benchmark in MLXHub and publish your result to add yours.

Your device

Where does your iPhone or iPad rank?

Download MLXHub and run the benchmark from the app. The app shows the same Top 10, and if your result is not in it, shows it below the list so you can compare.

Publishing a result is optional and requires an iCloud account.

About the results

How to read the ranking

Result labels

Not reviewed

Published and checked by the app, not yet reviewed. Included in the ranking.

Reviewed

Passed the automated consistency review.

Verified

Verified by the MLXHub team.

Weight of each metric in the global score

  • 30%Generation
  • 22%Usable memory
  • 15%Cold prompt processing
  • 15%Endurance
  • 10%Expert reading
  • 8%Model loading

Results are published by MLXHub users; the MLXHub team verifies them periodically, both manually and through automated reviews. Each row shows the best result published for one device model and memory size.

How the benchmark works

Ranking data

The ranking is published as a snapshot of results that passed the app's checks and were not removed by review. Scores are only comparable within the same benchmark version.

Data updated October 11, 2026 · Benchmark v1