Full build specs:
Haverworks Theseus75 keyboard + wrist rests
Brass plate with 70A mounting grommets
MTNU 800 keycaps (homage to the Atari 800)
HMX Cosmic Purple switches (205g0, TX films, Durock 63.5g slow springs)
Swagkeys Knight V4 stabilizers
MLPerf Inference 6.0 results are out! Lots of new goodness here, including a bunch of new benchmark tests (and models) and some very large clusters reaching new peak performance numbers.
🎉 MLPerf Mobile is now on the iOS App Store!
Run industry-standard ML benchmarks right from your iPhone.
See how your device performs — download it now 📲
https://apple.co/4bvbfdI
#MLPerf #AI #MachineLearning
MLPerf Mobile app v5.0.4 is here!
#MLPerf Mobile release now supports Samsung Exynos 2600 and Qualcomm's newest Snapdragon lineup, from flagship 8 Elite Gen 5 to mid-range 6 Gen 4. Meaning more comprehensive, apples-to-apples #AIperformance data across devices.
play.google.com/store/apps/d...
MLPerf Client v1.5 is out now. Updates include Windows ML support, GUI improvements, and experimental support for Linux and power-efficiency testing. We support a broad range of GPUs and NPUs across PCs, Macs, and iPad Pro. Free to download & run!
mlcommons.org/2025/11/mlpe...
4GT Sabre
Aluminum plate
HMX Hades V2 switches (205g0, TX films, Durock 63.5g slow springs)
TX AP screw-in stabs (205g0)
GMK British Racing Green R2
Walnut wrist rest from Digital Carpentry
We have released MLPerf Mobile v5.0.1 with support for MediaTek Dimensity 9400 SoCs and a few other improvements.
The app is available for Android phones via the Google Play Store and the MLCommons GitHub repo.
Let us know what you think!
t.co/715ENpV6W4
MLPerf Inference v5.1 results are out today! New in this round: DeepSeek R1, Whisper V3, and Llama 3.1 8B tests. A bunch of new GPUs were tested, including AMD MI355X, Nvidia GB300, and Intel Arc Pro B60.
mlcommons.org/2025/09/mlpe...
MLPerf Client 1.0 is out! Happy to see an AI benchmark that supports as many platforms and as scalable a set of workloads as this one does, plus the new GUI is extremely handy.
Yeah. It’s a funny thing to combine them.
Indeed.
Another recent arrival: QK Alice Duo.
Just arrived: the 4GT Sabre.
MLPerf Client v1.0 is out! 🎉
The new benchmark for LLMs on PCs and client systems is now available—featuring expanded model support, new workload scenarios, and broad hardware integration.
Thank you to all submitters! #AMD, #Intel, @microsoft.com, #NVIDIA, #Qualcomm
mlcommons.org/2025/07/mlpe...
MLPerf Client v1.0 is now available with a host of updates, including:
-A beta GUI
-3 new models
-Large ~4K/8K prompts
-GPU, NPU, & hybrid acceleration for all major PC hardware vendors
-Early Windows ML acceleration on Intel
-Win11 x64/Arm and macOS support
Happy to have MLPerf Mobile on the Play Store! Going forward, we're working to deliver proper hardware acceleration on new mobile devices as they hit the market, as well.
Don’t have a lift, so going with a shop.
Just got a stage-1 tune for my mk7 GTI. Need a beefier clutch to handle the torque.
As AI models grow, storage is key to #ML performance. MLCommons' @dkanter.bsky.social joins #Nutanix’s Tech Barometer podcast to explain why and how the #MLPerf #Storage #benchmark guides smarter #data #infrastructure for #AI.
Listen: www.nutanix.com/theforecastb...
#DataStorage #EnterpriseIT
Updated with support for Intel NPUs and more.
Ladies and gentlemen, the SplittyKitty. geekhack.org/index.php?to...
We have four new benchmarks this round as we work to keep pace with AI innovation:
-Llama 3.1 405B, our largest model yet
-Llama 2 70B interactive, with lower latency targets
-RGAT using a graph neural network
-Automotive PointPainting for edge devices
Progress over the past year includes a doubling of the median score per round for our Llama 2 70B LLM test, while the top score is over 3X faster now. This is the server scenario.
MLPerf Inference 5.0 results are out, with performance numbers for the latest AI accelerators, including AMD Instinct MI325X, Nvidia B200 and GB200, and Google TPU Trillium across a range of tests.
mlcommons.org/2025/04/mlpe...
Here’s the launch of my level 2 high-power certification flight: an Apogee Zephyr flying on an Aerotech J270 engine. Went to ~4500 feet; recovered it in good shape to pass the cert test.
