The Grux AI app's fit rule rates every model in its catalogue for a 16 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 16 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 16 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.
16 GB Mac: about 12 GB is available to a model.
The app would start this Mac on Grux Local 4B (great fit): ollama pull gruxai.com/grux/grux-local:4b
| Model | Memory it needs | Fit |
|---|---|---|
| Grux Local 4BOllama 0.40.8 or newer | 4.44 GB | Great fit |
| Grux Local 2BOllama 0.40.8 or newer | 2.65 GB | Great fit |
| Qwen 3.5 4BOllama 0.30.0 or newer | 4.4 GB | Great fit |
| Grux Local 9BOllama 0.40.8 or newer | 7.25 GB | Good fit |
| Qwen 3.5 2BOllama 0.30.0 or newer | 2.6 GB | Great fit |
| Qwen 3.5 9BOllama 0.30.0 or newer | 6.2 GB | Good fit |
| Llama 3.2 3B | 3 GB | Great fit |
| Qwen 3 VL 4BOllama 0.30.0 or newer | 6 GB | Good fit |
| Gemma 4 12BOllama 0.30.9 or newer | 9.4 GB | Tight |
Too big for this Mac: 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).
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 16 GB Mac can run, by the Grux AI app's fit rule (about 12 GB available to a model)
Start with: Grux Local 4B (ollama pull gruxai.com/grux/grux-local:4b)
Great fit: Grux Local 4B, Grux Local 2B, Qwen 3.5 4B, Qwen 3.5 2B, Llama 3.2 3B
Good fit: Grux Local 9B, Qwen 3.5 9B, Qwen 3 VL 4B
Tight: Gemma 4 12B
Too big: 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-16gb-mac/
From this size to the next one in the picker. The memory step chooser compares every larger size.
| Mac memory | The app starts it on | What changes from 16 GB |
|---|---|---|
| 18 GB2 GB more | Grux Local 4Bsame as on a 16 GB Mac | Qwen 3 VL 4B: Good fit to Great fit; Qwen 3.5 9B: Good fit to Great fit; Gemma 4 12B: Tight to Good fit |
8 GB, 18 GB, 24 GB, 32 GB, 36 GB, 48 GB, 64 GB, 96 GB, 128 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 |