This is the first in a series of build-log posts documenting a local LLM project, in which models are...
This is the first in a series of build-log posts documenting a local LLM project, in which models are run on owned consumer hardware rather than through a cloud API. The present entry covers the hardware, the software stack, and the benchmarks by which a primary model was selected.
The hardware
Two machines are used, both consumer-grade. All benchmarks reported below were obtained on the primary desktop.
Machine
Primary desktop
The first in a build-log series documenting a local LLM project. This entry covers the hardware, the software stack, and the…
The second entry in a build-log series on local LLMs: the two phases of inference, a controlled cross-machine benchmark, the disk…
A few years ago, "running an LLM on your own machine" mostly meant a slow, low-quality toy. That's no...
James O'Beirne's local-llm documents two builds for running large models at home, from a $2k dual-3090 rig to a $40k four-GPU…
The Problem With Choosing a Local Model Everyone has an opinion on which local LLM is...
A practical guide to running LLMs on budget hardware: real speeds, real stories, and real...
