Grux AI Download

Which local LLM can an 8 GB Mac run?

The Grux AI app's fit rule rates every model in its catalogue for an 8 GB Mac below, by the memory the model needs while it runs against about three quarters of the Mac's unified memory. The model the app starts an 8 GB Mac on is marked, with its Ollama pull line. The summary below the table is plain text to copy, and this address is the 8 GB result of the Mac picker, so it can be linked or shared. No speed is stated: speed depends on the chip, and only one Mac has been measured. A rating here says whether a model fits in memory, and nothing about how fast it runs or how well it answers.

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

Grux AI 3.3.1 · sources read 2026-11-19 · published 2026-11-19

What an 8 GB Mac can run

8 GB Mac: about 6 GB is available to a model.

The app would start this Mac on Grux Local 2B (great fit): ollama pull gruxai.com/grux/grux-local:2b

ModelMemory it needsFit
Grux Local 2BOllama 0.40.8 or newer2.65 GBGreat fit
Grux Local 4BOllama 0.40.8 or newer4.44 GBGood fit
Qwen 3.5 2BOllama 0.30.0 or newer2.6 GBGreat fit
Qwen 3.5 4BOllama 0.30.0 or newer4.4 GBGood fit
Llama 3.2 3B3 GBGood fit

Too big for this Mac: Qwen 3 VL 4B (6 GB), Grux Local 9B (7.25 GB), Qwen 3.5 9B (6.2 GB), Gemma 4 12B (9.4 GB), Mistral Small 3.2 24B (22 GB), GPT-OSS 20B (20 GB), Qwen 3.8 27B (17.4 GB), Gemma 4 26B (19.2 GB), Qwen 3 Coder 30B (28 GB), Qwen 3.5 35B (35 GB), Llama 3.3 70B (60 GB), GPT-OSS 120B (88 GB).

A summary to copy

Select the box and copy it. It is the result above as plain text, and every rating in it is the Mac picker's.

Which local LLMs an 8 GB Mac can run, by the Grux AI app's fit rule (about 6 GB available to a model)
Start with: Grux Local 2B (ollama pull gruxai.com/grux/grux-local:2b)
Great fit: Grux Local 2B, Qwen 3.5 2B
Good fit: Grux Local 4B, Qwen 3.5 4B, Llama 3.2 3B
Tight: none
Too big: Qwen 3 VL 4B, Grux Local 9B, Qwen 3.5 9B, Gemma 4 12B, Mistral Small 3.2 24B, GPT-OSS 20B, Qwen 3.8 27B, Gemma 4 26B, Qwen 3 Coder 30B, Qwen 3.5 35B, Llama 3.3 70B, GPT-OSS 120B
Rated by memory only, not speed.
https://gruxai.com/answers/local-llm-for-a-8gb-mac/

What the next size up changes

From this size to the next one in the picker. The memory step chooser compares every larger size.

Mac memoryThe app starts it onWhat changes from 8 GB
16 GB8 GB moreGrux Local 4BLlama 3.2 3B: Good fit to Great fit; Qwen 3.5 4B: Good fit to Great fit; Grux Local 4B: Good fit to Great fit; Qwen 3 VL 4B: Too big to Good fit; Qwen 3.5 9B: Too big to Good fit; Grux Local 9B: Too big to Good fit; Gemma 4 12B: Too big to Tight

Other memory sizes

16 GB, 18 GB, 24 GB, 32 GB, 36 GB, 48 GB, 64 GB, 96 GB, 128 GB

What this page does not cover

Where to check this

ClaimSource
The fit rule and every model's serving memoryGrux Cookbook.swift at the pinned commit
A Mac's model budget is a share of its unified memory, which Metal reports for each GPUApple, recommendedMaxWorkingSetSize

Questions

How does this page rate a model for an 8 GB Mac?
By the memory the model needs while it runs, against about three quarters of the Mac's 8 GB of unified memory. It is the Mac picker's rule and the Grux AI app's, and the table gives each model's rating.
Does this page say how fast a model runs?
No. It rates fit by memory. The one Mac measured for this site is a 16 GB Apple M4 Mac mini, on the Grux Local speed page.
Where do the ratings come from?
From the Grux AI app's own catalogue and fit rule, read from its public source at one pinned commit, shown in the sources table on this page.
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.