lukasonedge
Re:Show HN: Compute:Arena – Community submitted local AI benchmarks
on Thursday September 17, 2026 @07:53PM (#49748425)
all runs are cryptographically hashed so users can't tamper. Thermals and peak memory is logged as well. Example: https://computearena.ai/benchmarks/de2ccdb2-c0a9-431b-8e0a-3...
Re:Show HN: Compute:Arena – Community submitted local AI benchmarks
on Thursday September 17, 2026 @02:55AM (#49737291)
i didn't recognise some of the models on the frontpage
Re:State of Local AI Report
on Tuesday September 01, 2026 @09:12PM (#49530527)
good overview of hardware and models
Show HN: Zero () friction local AI for Mac
https://www.basecompute.co/local
Super excited to launch our new app Local today. What we’ve learned at Base Compute over the last months is that running AI directly on your laptop or workstation gives you maximum privacy and it’s free, but it’s also a massive headache to configure. So we’ve decided what matters is making the experience completely frictionless for users.Local analyses the hardware of your laptop, optimises the...
Re:Fastest Inference Meta Muse Glimmer 30B on Apple
on Tuesday August 11, 2026 @10:46PM (#49267282)
hey guys, we've optimised our inference engine to run Meta Muse Glimmer 30B faster than any other engine (llama.cpp etc) on Mac. Best performance on M5 Pro.