Claude Desktop Cowork Feature Creates 10GB VM Bundle Causing Severe Performance Issues
By
mystcb
More flour than flavour. There's a bagel in here, just not much of one.
Summary
The article documents a performance issue with Claude Desktop's cowork feature, which creates a 10GB VM bundle file that never gets cleaned up, causing severe performance degradation including slow startup, UI lag, and slow responses. The investigation reveals that deleting the vm_bundles directory and cache files results in immediate ~75% performance improvement, but the problem recurs as the VM bundle regenerates quickly.
Key quotes
· 4 pulledAfter using the cowork feature, Claude Desktop becomes extremely slow - slow startup, UI lag, and slow responses.
The cowork feature creates a VM bundle at: ~/Library/Application Support/Claude/vm_bundles/claudevm.bundle/rootfs.img
This file grows to 10GB and is never cleaned up. It regenerates quickly after deletion (deleted one day, back to 10GB the next).
Deleted vm_bundles, Cache, and Code Cache directories (reduced from 11GB to 639MB). Result: ~75% faster immediate
You might also wanna read
Optimizing .NET APIs for High Throughput: Techniques for 1M Requests Per Minute
Article discusses techniques for designing high-throughput .NET APIs capable of handling 1M requests per minute. It covers horizontal scalin
blog.elmah.io·21h ago
How micro-optimizations in Azure Service Bus SDK paved the way for a smarter redesign
The article discusses how micro-optimizations in the Azure Service Bus SDK led to meaningful design improvements. Rather than advocating for
How Kestra Improved Orchestrator Performance Across 14 Releases: A Year of Performance Engineering
Kestra's engineering team details their year-long performance engineering journey across releases 0.19 to 1.3, treating performance as an on
medium.com·2d ago
Optimizing Deep Learning Performance Through First-Principles Reasoning
The article discusses improving deep learning model performance by reasoning from first principles rather than relying on ad-hoc tricks and
Java Performance Optimization: Fixing 8 Common Anti-Patterns to Reduce Processing Time by 80%
The article presents a case study of Java performance optimization where fixing common anti-patterns dramatically improved application perfo
jvogel.me·2mo ago
Understanding CPU Branch Prediction and Its Impact on Benchmarking
The article discusses how modern processors use branch prediction to execute multiple instructions per cycle, explaining that CPUs have rema
lemire.me·2mo ago