Yes. macOS lets the GPU use only part of a Mac's unified memory, holding roughly a quarter to a third of it back by default, varying from Mac to Mac, and the owner can raise that limit with one setting, iogpu.wired_limit_mb, until the next restart. On the 16 GB Apple M4 Mac mini measured for this page, Metal reported 11.84 GiB, 74 percent of its memory, with the setting at 0, which means the default is in force. A local model that is Too big or Tight at the Mac picker's budget can rate higher at a larger limit, and the table below works out which, for every Apple memory size and three larger limits, with the same fit rule as the Mac picker. The price is what is left for macOS and your other apps, which the table shows beside each limit. The setting is described in an open Ollama pull request, not in Apple's documentation, so it is a power user's lever and this page recommends no value.
Apple's Metal reports a recommended maximum working set size for each GPU: the memory a model may use without affecting its runtime performance, in Apple's words. The Mac picker rates models against 75 percent of unified memory. One Mac was measured for this page, and it agrees with that share. No other Mac was measured.
| What was read | Value |
|---|---|
| Mac | Apple M4 Mac mini, 16 GB, macOS 26.3.1 |
| Metal's recommended maximum working set size | 11.84 GiB, 74 percent of its memory |
| The iogpu.wired_limit_mb setting | 0, so the default is in force |
| Read on | 2026-11-19, with no model loaded |
Ollama's documentation does not describe this yet. An open pull request, ollama/ollama 19527, proposes the text. It says:
total= figure in the inference compute line of the Ollama server log. The same pull request measured it rising from 17.8 GiB to 20.0 GiB on a 24 GB Mac after the limit was raised.iogpu.wired_limit_mb in megabytes, which is the limit in GB times 1024.ollama stop <model>, or restart Ollama, so the next load uses the new limit.sysctl iogpu.wired_limit_mb # 0 means macOS's default is in force
sudo sysctl iogpu.wired_limit_mb=<MB> # MB = GB x 1024, until the next restart
sudo sysctl iogpu.wired_limit_mb=0 # back to the default
Choose your Mac's memory. Each row is the Mac picker's rule with a larger share of memory as the limit. The first row is the picker's own 75 percent budget; your Mac's default may be a little lower or higher. The last column lists the models whose rating changes from that row, and the middle column is the memory left for macOS and everything else you run. The pull request warns that a limit set too high can cause heavy swapping, so a row with little left is a risk, not a target. Nothing here recommends a row.
8 GB Mac: at the Mac picker's budget a model may use about 6 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 6 GB | 2 GB | Same ratings as the Mac picker. |
| 80 percent6.4 GB | 1.6 GB | Llama 3.2 3B: Good fit to Great fit; Qwen 3 VL 4B: Too big to Tight |
| 85 percent6.8 GB | 1.2 GB | Llama 3.2 3B: Good fit to Great fit; Qwen 3 VL 4B: Too big to Tight; Qwen 3.5 9B: Too big to Tight |
| 90 percent7.2 GB | 0.8 GB | Llama 3.2 3B: Good fit to Great fit; Qwen 3 VL 4B: Too big to Tight; Qwen 3.5 9B: Too big to Tight |
16 GB Mac: at the Mac picker's budget a model may use about 12 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 12 GB | 4 GB | Same ratings as the Mac picker. |
| 80 percent12.8 GB | 3.2 GB | 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 |
| 85 percent13.6 GB | 2.4 GB | 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 |
| 90 percent14.4 GB | 1.6 GB | 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 |
18 GB Mac: at the Mac picker's budget a model may use about 13.5 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 13.5 GB | 4.5 GB | Same ratings as the Mac picker. |
| 80 percent14.4 GB | 3.6 GB | No model changes rating. |
| 85 percent15.3 GB | 2.7 GB | Grux Local 9B: Good fit to Great fit |
| 90 percent16.2 GB | 1.8 GB | Grux Local 9B: Good fit to Great fit |
24 GB Mac: at the Mac picker's budget a model may use about 18 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 18 GB | 6 GB | Same ratings as the Mac picker. |
| 80 percent19.2 GB | 4.8 GB | Gemma 4 12B: Good fit to Great fit; Qwen 3.8 27B: Too big to Tight |
| 85 percent20.4 GB | 3.6 GB | Gemma 4 12B: Good fit to Great fit; Qwen 3.8 27B: Too big to Tight; Gemma 4 26B: Too big to Tight |
| 90 percent21.6 GB | 2.4 GB | Gemma 4 12B: Good fit to Great fit; Qwen 3.8 27B: Too big to Tight; Gemma 4 26B: Too big to Tight; GPT-OSS 20B: Too big to Tight |
32 GB Mac: at the Mac picker's budget a model may use about 24 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 24 GB | 8 GB | Same ratings as the Mac picker. |
| 80 percent25.6 GB | 6.4 GB | Gemma 4 26B: Tight to Good fit |
| 85 percent27.2 GB | 4.8 GB | Gemma 4 26B: Tight to Good fit; GPT-OSS 20B: Tight to Good fit |
| 90 percent28.8 GB | 3.2 GB | Gemma 4 26B: Tight to Good fit; GPT-OSS 20B: Tight to Good fit |
36 GB Mac: at the Mac picker's budget a model may use about 27 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 27 GB | 9 GB | Same ratings as the Mac picker. |
| 80 percent28.8 GB | 7.2 GB | No model changes rating. |
| 85 percent30.6 GB | 5.4 GB | Mistral Small 3.2 24B: Tight to Good fit; Qwen 3 Coder 30B: Too big to Tight |
| 90 percent32.4 GB | 3.6 GB | Mistral Small 3.2 24B: Tight to Good fit; Qwen 3 Coder 30B: Too big to Tight |
48 GB Mac: at the Mac picker's budget a model may use about 36 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 36 GB | 12 GB | Same ratings as the Mac picker. |
| 80 percent38.4 GB | 9.6 GB | Gemma 4 26B: Good fit to Great fit; Qwen 3 Coder 30B: Tight to Good fit; Qwen 3.5 35B: Too big to Tight |
| 85 percent40.8 GB | 7.2 GB | Gemma 4 26B: Good fit to Great fit; GPT-OSS 20B: Good fit to Great fit; Qwen 3 Coder 30B: Tight to Good fit; Qwen 3.5 35B: Too big to Tight |
| 90 percent43.2 GB | 4.8 GB | Gemma 4 26B: Good fit to Great fit; GPT-OSS 20B: Good fit to Great fit; Qwen 3 Coder 30B: Tight to Good fit; Qwen 3.5 35B: Too big to Tight |
64 GB Mac: at the Mac picker's budget a model may use about 48 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 48 GB | 16 GB | Same ratings as the Mac picker. |
| 80 percent51.2 GB | 12.8 GB | No model changes rating. |
| 85 percent54.4 GB | 9.6 GB | No model changes rating. |
| 90 percent57.6 GB | 6.4 GB | Qwen 3 Coder 30B: Good fit to Great fit |
96 GB Mac: at the Mac picker's budget a model may use about 72 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 72 GB | 24 GB | Same ratings as the Mac picker. |
| 80 percent76.8 GB | 19.2 GB | No model changes rating. |
| 85 percent81.6 GB | 14.4 GB | Llama 3.3 70B: Tight to Good fit |
| 90 percent86.4 GB | 9.6 GB | Llama 3.3 70B: Tight to Good fit |
128 GB Mac: at the Mac picker's budget a model may use about 96 GB.
| Limit | Left for macOS and apps | What changes from the first row |
|---|---|---|
| 75 percent, the Mac picker's budgetabout 96 GB | 32 GB | Same ratings as the Mac picker. |
| 80 percent102.4 GB | 25.6 GB | No model changes rating. |
| 85 percent108.8 GB | 19.2 GB | No model changes rating. |
| 90 percent115.2 GB | 12.8 GB | No model changes rating. |
total= line after a change.| Claim | Source |
|---|---|
| Metal reports a recommended maximum working set size for the GPU | Apple, recommendedMaxWorkingSetSize |
| The setting, macOS 14 or later, the reset at reboot, 0 for the default, and the measured case | Ollama pull request 19527 |
| Another fit calculator limits memory to a percentage in its estimates | llmfit pull request 1089 |
| The fit rule and every model's serving memory | Grux Cookbook.swift at the pinned commit |