~/series/ local-ai-hardware-tested

Local AI Hardware, Tested

Series · 3

2026-10-18
Is a Mac actually good for local LLMs
Apple says the Mac mini offers "fast, private, on-device inference" and up to 13.5x faster LLM prompt processing; NVIDIA says the RTX 5090 Laptop GPU has 1,824 AI TOPS. What they compare against, how the test machines were configured, and the three numbers that decide how fast a model actually feels — memory bandwidth, the compute for reading prompts, and how much memory the GPU can really use — are not where you look first. Using the llama.cpp community's shared benchmarks across dozens of machines, a check on two machines of my own, and a re-run of Apple's own footnoted test on the 16 GB base model, and the coding, compiling and testing work where the Mac mini measurably wins, this post answers, case by case, what a Mac mini, a Mac Studio and each class of NVIDIA card are actually good for.
Local AI Hardware, Tested #Local LLM #Hardware #Apple Silicon #NVIDIA
2026-10-30
Half-rate tensor cores, explained
NVIDIA makes the same chip into gaming cards and professional cards, and on the gaming cards the tensor cores, the part built for AI math, ship set to half speed. In October 2026 an open-source project called gpu-unlock lifted that lock. This is the illustrated beginner edition. No registers and no code; just where the story comes from, where the lock sits, what I measured on my own laptop, and what it means for everyone else.
Local AI Hardware, Tested #GPU #NVIDIA #Tensor Cores #Local AI
2026-10-29
The half-speed tensor core
gpu-unlock, the open-source project that went viral in October 2026, lifts the half-rate cap NVIDIA puts on tensor math on consumer GPUs (FP16, BF16 and TF32 on RTX 30/40; FP16 only on RTX 20). I measured it on my own RTX 3060 laptop. At the same power draw, about 105 W, BF16 matrix multiply went from 25 to 42 TFLOPS and a small training run got 40% faster, while the FP32 and INT8 controls did not move. The post explains which part of the hardware is capped, why the laptop got about 1.6x instead of a doubling, how the cap is opened before the GPU driver loads, why RTX 50 cannot be unlocked, and the history of similar bypasses.
Local AI Hardware, Tested #GPU #NVIDIA #Tensor Cores #Local AI

Is a Mac actually good for local LLMs

Half-rate tensor cores, explained

The half-speed tensor core