Skip to main content
General
July 16, 2026
10 min read

Benchmarking Local LLMs Across an RTX 3060 Ti and an M4 Mac Mini (With a Kernel Panic Along the Way)

A deep benchmarking session across two very different machines turned up an 8.5x speedup hiding in a single misconfigured setting, a genuine MLX advantage over GGUF, and one crash that took down an entire Mac Mini.

Words

1,858

Read Time

10 min read

Category

General

Read aloud
Browser TTS unavailable
Ready for a more natural read-aloud pass.
Reading list
Reading History

Recent articles you open here will appear in this quick history.

#AI#Ollama#MLX#Benchmarking#Homelab#Machine Learning+1
Loading article…

Continue Reading

These are close to this article’s reading time, so they make a good next step without a big context switch.