Best local LLM hardware
Curated picks by budget and use case, with the reasons behind each choice.
- Best graphics cards for local LLMsThe cards worth buying for running language models at home, from a used RTX 3090 to 96 GB.RTX 3090 · Radeon AI PRO R9700 · RTX 5090 …
- Best hardware to run gpt-oss-120b locallygpt-oss-120b needs about 65 GB with a 32K context. These are the machines that hold it, from cheapest to fastest.Ryzen AI Max+ 395 · Mac Studio M5 Max · DGX Spark / GB10 …
- Best budget hardware for local LLMsCheap ways to start: 12–16 GB cards and small machines that run 8–14B models well.RTX 5060 Ti 16 GB · RX 9060 XT 16 GB · RTX 3060 12 GB …
- Best mini PCs and small machines for local LLMsUnified-memory boxes that run big models quietly on a shelf: Strix Halo, Mac and DGX Spark.Ryzen AI Max+ 395 · Mac Studio M5 Max · Mac mini M5 Pro …