Codex Desktop can drive 60-80% GPU usage on M4 Max during subagent-heavy sessions
What version of Codex is running?
Codex Desktop 0.122.0-alpha.1
Which model were you using?
gpt-5.4 with high reasoning
What platform is your computer?
macOS on a MacBook Pro with M4 Max and 64 GB memory
What issue are you seeing?
Codex is using an unexpectedly large amount of GPU during a real coding session. On this machine I saw sustained GPU usage around 60-80%, which feels far out of proportion to the work being done.
I do not have direct GPU telemetry from the session logs themselves, but I do have the exact Codex session/thread that triggered it and the local session metadata.
What steps can reproduce the bug?
The exact session that triggered this was:
- Session/thread ID:
019d97b1-82c6-7d01-9042-030f94e105bc - Thread name:
Plan audit fix proposal - Session start: April 16, 2026 at 19:08:06 UTC
- Source:
vscode - Working directory at the time:
/Users/treygoff/Code/atlasos
From the local session trace, this thread then spawned four subagents in quick succession at approximately April 16, 2026 19:09:28 UTC:
Descartes(explorer)McClintock(explorer)Lagrange(explorer)Plan Critic(plan_checker)
All of those subagents were launched with gpt-5.4 and high reasoning.
A plausible repro pattern seems to be:
- Use Codex Desktop on macOS in a VS Code-originated session.
- Start a task that triggers multiple high-effort subagents in parallel.
- Keep the session open while they run and report back.
- Observe GPU usage in Activity Monitor.
On my machine, GPU usage climbed to roughly 60-80% during this workload.
What is the expected behavior?
Even when a session is doing substantial reasoning or coordinating several subagents, local GPU usage should stay much lower unless there is a clearly necessary rendering workload.
What do you see instead?
Codex appears to drive very high GPU usage during this session pattern, despite the task being primarily text/orchestration work.
Additional information
A few concrete data points from the session metadata:
- Parent thread model:
gpt-5.4 - Parent thread reasoning:
high - Parent thread source:
vscode - The issue was observed on an M4 Max MacBook Pro with 64 GB RAM, so this is not extremely constrained hardware.
If useful, I can provide more local session artifacts tied to 019d97b1-82c6-7d01-9042-030f94e105bc.
3 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
<img width="1594" height="752" alt="Image" src="https://github.com/user-attachments/assets/cd19a592-2bc2-4ef3-89bf-c85caba72752" />
Additional reproducible data point on macOS:
Codex Service was consuming approximately 36–37% GPU while the Subagents panel was visible. Closing the Subagents panel caused the GPU usage to drop; reopening it caused the high GPU usage to return.
The panel contained ~40 active subagents, but the agents continued running when the panel was closed, so the GPU utilization appears specifically correlated with rendering/displaying the Subagents UI rather than subagent execution itself.
Activity Monitor also showed significant WindowServer GPU utilization at the same time.
This looks like a continuously invalidating/rendering Subagents view, animation, compositing loop, or similar UI-side issue.