[Performance] Extreme CPU/RAM usage and thermal throttling on Apple Silicon since v2.1.4
Preflight Checklist
- [x] I have searched existing issues and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
What's Wrong?
Since version 2.1.4, Claude Code causes extremely high CPU and RAM usage on my MacBook Air M4, resulting in severe overheating and thermal throttling.
Key observations:
- Running a single Claude Code instance (no parallel operations)
- Issue persists across all terminals: VS Code, Warp, native zsh
- Device becomes nearly unusable due to thermal throttling
- Previous versions (before 2.1.4) did not have this problem
What Should Happen?
Claude Code should maintain reasonable CPU and RAM usage that doesn't cause thermal throttling on Apple Silicon devices during normal single-instance usage. Previous versions (before 2.1.4) worked
fine without overheating issues.
Error Messages/Logs
Steps to Reproduce
- Use MacBook Air M4 (or other Apple Silicon device)
- Open any terminal (VS Code terminal, Warp, or native zsh)
- Navigate to any project directory
- Run
claudeto start Claude Code - Send a few simple prompts (nothing complex, no parallel tasks)
- Observe CPU/RAM usage spike in Activity Monitor
- Notice device heating up significantly and performance degrading due to thermal throttling
Note: No special code or files needed - the issue occurs with any normal usage.
Claude Model
Opus
Is this a regression?
Yes, this worked in a previous version
Last Working Version
2.1.3
Claude Code Version
2.1.4
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
VS Code integrated terminal
Additional Information
- Device: MacBook Air M4
- The overheating is severe enough to cause thermal throttling, making the device nearly unusable
- Only running a single Claude Code instance with no parallel operations
- This is not terminal-specific as it happens in VS Code, Warp, and native Terminal
- The issue significantly impacts productivity due to performance degradation from thermal throttling
This issue has 6 comments on GitHub. Read the full discussion on GitHub ↗