Grux AI Download

Can an Intel Mac run local AI?

An Intel Mac can run a local LLM, but only through Ollama, and only on the CPU. Ollama's macOS documentation lists x86 as CPU only and requires macOS Sonoma (14) or newer, so the Intel Macs that qualify are the 2018 to 2020 MacBook Pro and MacBook Air, the 2018 Mac mini, the 2019 and 2020 iMac, the 2017 iMac Pro and the 2019 Mac Pro. LM Studio supports Apple silicon only, Jan stopped running local models on Intel Macs at v0.8.5, and Grux AI is Apple silicon only. On an Intel Mac, install Ollama and start with a small model, 2b to 4b parameters. This page quotes no speed, because we have not measured an Intel Mac.

Download Grux AI 3.3.1, free, for macOS 14 or later on Apple silicon.

Grux AI 3.3.1 · last checked 2026-11-13 · generated from the shipping release

Which apps run on an Intel Mac

AppLocal models on an Intel MacWhat its own documentation says
OllamaYes, CPU onlymacOS 14 or newer; Apple M series (CPU and GPU) or x86 (CPU only)
LM StudioNoChip: Apple silicon (M1 to M4); Intel-based Macs are not supported
JanNo, since v0.8.5Intel Macs unsupported since v0.8.0; since v0.8.5 local models do not run on them
Grux AINomacOS 14 or later, Apple silicon
GPT4AllNot tested heremacOS 12.6 or newer, best results with Apple silicon; its README does not say Intel is excluded

Ollama is the one runner here that documents an Intel path. GPT4All's README does not exclude Intel Macs, and we have not run it on one, so treat that row as unverified.

Which Intel Macs can install Ollama

Ollama's Mac app needs macOS Sonoma. Apple lists these Intel models as compatible with Sonoma; an older Intel Mac stops short of it and cannot install the app.

ModelIntel years that run Sonoma
MacBook Pro13-inch and 15-inch 2018 and 2019, 16-inch 2019, 13-inch 2020 (Intel)
MacBook AirRetina 13-inch 2018, 2019 and 2020 (Intel)
iMacRetina 4K 21.5-inch 2019, Retina 5K 27-inch 2019 and 2020
Mac mini2018
iMac Pro and Mac ProiMac Pro 2017, Mac Pro 2019

Start with a small model

Without a GPU, memory bandwidth and the CPU set the pace, so pick the smallest models. The sizes below are from the Ollama library, the same ones used on the MacBook Air page.

brew install ollama
ollama run gemma3:4b       # a 3.3GB download
ollama run qwen3.5:2b      # about 2.7GB to 3.1GB

How fast these answer on an Intel Mac depends on the chip and the memory, and we have not measured it, so no figure is quoted. If a reply is too slow, go one size down.

If you want the agent, not only a chat

Grux AI acts on mail, calendar, files and the shell, and it needs Apple silicon. The which LLM can my Mac run page lists what each Apple silicon memory size runs, for the day you move to one.

Where to check this

ClaimSource
macOS 14 or newer; x86 is CPU onlyOllama documentation, macOS
Apple silicon only; Intel-based Macs are not supportedLM Studio, system requirements
Local models do not run on Intel Macs since v0.8.5Jan, Mac installation
The Macs that run SonomaApple Support, macOS Sonoma compatible computers
macOS 12.6 or newer, best results with Apple siliconGPT4All README
Grux AI is Apple silicon onlyGrux README, Requirements

Questions

Does Ollama work on an Intel Mac?
Yes, on the CPU only, and it needs macOS Sonoma (14) or newer. Intel Macs from 2018 to 2020 qualify; older ones cannot install the app.
Does LM Studio run on an Intel Mac?
No. Its system requirements list Apple silicon only and say Intel-based Macs are not supported.
Does Jan run on an Intel Mac?
Not for local models. Jan's documentation says local models do not run on Intel Macs since v0.8.5.
Can Grux AI run on an Intel Mac?
No. Grux AI needs Apple silicon.
Download Grux AI 3.3.1 Read the source

Free, MIT licensed. macOS 14 or later, Apple silicon. 29.1 MB, signed and notarized by Apple. No account, no server, no subscription.