The Grux AI app's fit rule rates every model in its catalogue for a 128 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 a 128 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 128 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.
128 GB Mac: about 96 GB is available to a model.
The app would start this Mac on Grux Local 9B (great fit): ollama pull gruxai.com/grux/grux-local:9b
| Model | Memory it needs | Fit |
|---|---|---|
| Grux Local 9BOllama 0.40.8 or newer | 7.25 GB | Great fit |
| Grux Local 4BOllama 0.40.8 or newer | 4.44 GB | Great fit |
| Gemma 4 26BOllama 0.30.9 or newer | 19.2 GB | Great fit |
| Grux Local 2BOllama 0.40.8 or newer | 2.65 GB | Great fit |
| Gemma 4 12BOllama 0.30.9 or newer | 9.4 GB | Great fit |
| Qwen 3.8 27BOllama 0.32.12 or newer | 17.4 GB | Great fit |
| Qwen 3.5 4BOllama 0.30.0 or newer | 4.4 GB | Great fit |
| Qwen 3.5 9BOllama 0.30.0 or newer | 6.2 GB | Great fit |
| Qwen 3.5 35BOllama 0.30.0 or newer | 35 GB | Great fit |
| Qwen 3 Coder 30B | 28 GB | Great fit |
| GPT-OSS 20BOllama 0.30.0 or newer | 20 GB | Great fit |
| Mistral Small 3.2 24B | 22 GB | Great fit |
| Qwen 3.5 2BOllama 0.30.0 or newer | 2.6 GB | Great fit |
| Llama 3.2 3B | 3 GB | Great fit |
| Llama 3.3 70B | 60 GB | Good fit |
| Qwen 3 VL 4BOllama 0.30.0 or newer | 6 GB | Great fit |
| GPT-OSS 120BOllama 0.30.0 or newer | 88 GB | Tight |
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 a 128 GB Mac can run, by the Grux AI app's fit rule (about 96 GB available to a model)
Start with: Grux Local 9B (ollama pull gruxai.com/grux/grux-local:9b)
Great fit: Grux Local 9B, Grux Local 4B, Gemma 4 26B, Grux Local 2B, Gemma 4 12B, Qwen 3.8 27B, Qwen 3.5 4B, Qwen 3.5 9B, Qwen 3.5 35B, Qwen 3 Coder 30B, GPT-OSS 20B, Mistral Small 3.2 24B, Qwen 3.5 2B, Llama 3.2 3B, Qwen 3 VL 4B
Good fit: Llama 3.3 70B
Tight: GPT-OSS 120B
Too big: none
Rated by memory only, not speed.
https://gruxai.com/answers/local-llm-for-a-128gb-mac/
From this size to the next one in the picker. The memory step chooser compares every larger size.
128 GB is the largest size in the picker, so there is no larger size to compare. The Mac Studio page rates the configurations above it with the same rule.
8 GB, 16 GB, 18 GB, 24 GB, 32 GB, 36 GB, 48 GB, 64 GB, 96 GB
| Claim | Source |
|---|---|
| The fit rule and every model's serving memory | Grux Cookbook.swift at the pinned commit |
| A Mac's model budget is a share of its unified memory, which Metal reports for each GPU | Apple, recommendedMaxWorkingSetSize |