Issue Station
Sign In
Tools hereToolbox

gemini-cli - 💡(How to fix) Fix Extremely slow [5 comments, 5 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
google-gemini/gemini-cli#25007•Fetched 2026-04-10 03:45:31
View on GitHub
Comments
5
Participants
5
Timeline
9
Reactions
0
Author
vvantvvant
Participants
AlhiefikriAlhiefikribillouetaudreybillouetaudreygemini-cli[bot]gemini-cli[bot]HPSDfHPSDfvvantvvant
Timeline (top)
commented ×5labeled ×3subscribed ×1
RAW_BUFFERClick to expand / collapse

What happened?

Gemini CLI is extremely slow. Painfully slow session details:

Interaction Summary │ │ Session ID: 79f0eaba-7ab9-4047-a697-8a32a7501680 │ │ Tool Calls: 59 ( ✓ 55 x 4 ) │ │ Success Rate: 93.2% │ │ User Agreement: 100.0% (58 reviewed) │ │ Code Changes: +907 -370 │ │ │ │ Performance │ │ Wall Time: 11h 5m 13s │ │ Agent Active: 1h 47m 1s │ │ » API Time: 1h 39m 4s (92.6%) │ │ » Tool Time: 7m 57s (7.4%) │ │ │ │ Model Reqs Input Tokens Cache Reads Output Tokens │ │ ──────────────────────────────────────────────────────────────────────── │ │ gemini-2.5-flash-lite 15 151,243 0 1,051 │ │ gemini-3-flash-preview 34 433,137 1,122,146 29,755 │ │ gemini-3.1-pro-preview 84 869,704 3,456,284 26,197 │ │ gemini-3.1-pro 2 0 0 0 │ │ │ │ Savings Highlight: 4,578,430 (75.9%) of input tokens were served from the cache, reducing costs. │

What did you expect to happen?

Expected regular waiting time. Each request took 5+ minutes

Client information

  • CLI Version: 0.36.0
  • Git Commit: 8b1e649c2
  • Session ID: 9a4d864f-9da1-484f-9ed9-39b3ae1c11ca
  • Operating System: darwin v25.8.2
  • Sandbox Environment: no sandbox
  • Model Version: gemini-3.1-pro-preview
  • Auth Type: oauth-personal
  • Memory Usage: 431.1 MB
  • Terminal Name: Unknown
  • Terminal Background: #ffffff
  • Kitty Keyboard Protocol: Unsupported

Login information

Google Account

Anything else we need to know?

No response

extent analysis

TL;DR

The Gemini CLI slowness may be mitigated by investigating the high API Time and optimizing the model usage, particularly for the gemini-3.1-pro-preview model.

Guidance

  • Investigate the API Time of 1h 39m 4s (92.6% of Agent Active time) to identify potential bottlenecks in the API requests.
  • Review the model usage, especially for gemini-3.1-pro-preview, which has a high number of requests (84) and cache reads (3,456,284).
  • Consider optimizing the input tokens or model configuration to reduce the load on the API and improve performance.
  • Verify if the slowness is specific to the gemini-3.1-pro-preview model or if other models are also experiencing similar issues.

Notes

The provided information suggests that the slowness is related to the API Time and model usage, but further investigation is needed to determine the root cause.

Recommendation

Apply workaround: Optimize model usage and investigate API Time bottlenecks, as the root cause of the slowness is likely related to these factors.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#permission error#memory optimization#batch processing#GPU compatibility

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING