# Critical Performance Issue: Gemini 3.8 Flash Extremely Slow in Antigravity IDE

**URL:** <https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333>\
**Category:** Google Antigravity\
**Tags:** gemini-flash\
**Created:** [November 5, 2026, 6:50am UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333 "2026-11-05T06:50:53Z")\
**Posts on this page:** 12\
**Page:** 1

<div class="post-metadata">

**Author:** ![YouTube\_Prime](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/youtube_prime/32/165609_2.png) [@YouTube\_Prime](https://discuss.ai.google.dev/u/YouTube_Prime)\
**Post date:** [November 5, 2026, 6:50am UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/1 "2026-11-05T06:50:53Z")

</div>

ello Google Antigravity Engineering Team,

I am experiencing a serious performance issue with Gemini 3.8 Flash inside Antigravity IDE.

### Problem Description

Gemini 3.8 Flash takes an unusually long time to respond, even to very simple prompts such as:

- Hi

- Hello

- Simple coding questions

The model sometimes remains in the Working state for an extended period before generating a response.

### Expected Behaviour

Gemini 3.8 Flash should respond quickly to simple prompts and provide reasonable response times for coding tasks.

### Actual Behaviour

- Very high initial response latency.

- Slow response generation.

- Simple prompts take an unusually long time.

- Other available AI models work normally in the same Antigravity environment.

### Environment

- IDE: Google Antigravity

- Operating System: Ubuntu Linux

- Model: Gemini 3.8 Flash

- Antigravity Version: [Enter your installed version]

### Troubleshooting Already Attempted

- Restarted Antigravity.

- Tested with a new conversation.

- Compared response times with other AI models.

The issue appears to be specific to Gemini 3.8 Flash rather than my local machine or internet connection.

### Request

Could the engineering team investigate the Gemini 3.8 Flash latency and streaming performance inside Antigravity?

Please provide an update or workaround.

---

<div class="post-metadata">

**Author:** ![discourse\_ai\_spam](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/discourse_ai_spam/32/32411_2.png) [@discourse\_ai\_spam](https://discuss.ai.google.dev/u/discourse_ai_spam)\
**Post date:** [November 5, 2026, 6:50am UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/2 "2026-11-05T06:50:56Z")

</div>

Unlisted on November 5, 2026, 6:50am UTC



---

<div class="post-metadata">

**Author:** ![system](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/system/32/1_2.png) [@system](https://discuss.ai.google.dev/u/system)\
**Post date:** [November 5, 2026, 6:52am UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/3 "2026-11-05T06:52:07Z")

</div>

Listed on November 5, 2026, 6:52am UTC



---

<div class="post-metadata">

**Author:** ![Tran\_Tran](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/tran_tran/32/161275_2.png) [@Tran\_Tran](https://discuss.ai.google.dev/u/Tran_Tran)\
**Post date:** [November 5, 2026, 11:05am UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/4 "2026-11-05T11:05:18Z")

</div>

Agree, mine’s like freezing now

---

<div class="post-metadata">

**Author:** ![Ahmed\_Shaban2](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/ahmed_shaban2/32/165833_2.png) [@Ahmed\_Shaban2](https://discuss.ai.google.dev/u/Ahmed_Shaban2)\
**Post date:** [November 5, 2026, 1:00pm UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/5 "2026-11-05T13:00:03Z")

</div>

Subject: Gemini 3.8 Flash — 2–5 min latency for trivial prompts, no error shown (reproducible today)

Model: gemini-3.8-flash-low and gemini-3.8-flash-medium (both show the same behavior)  
IDE: Antigravity IDE 2.13.0, Windows 11  
Account plan: Google AI Pro  
Region: Egypt (direct network access, no VPN/proxy)  
Repro session: 20261105T143557 (Nov 5, 2026, ~14:35 UTC+2), workspace on a small React project

Symptom:  
Every prompt — including a bare “Hello” — takes 2–5 minutes before the  
first token arrives. The panel stays in “Working” state with no visible  
error. Local machine, auth, and network are healthy (RTT to Google  
endpoints ~1s, no proxy).

Local diagnostics:  
Language server and auth initialize in under a second; no 503 or retry  
lines appear in local logs at default verbosity (2.13 appears to run the  
agent cloud-side, so backend failures are silent).

Not local: other models respond in seconds on the same machine and  
connection.

Same reports, growing daily:

- GitHub issue google-antigravity/antigravity-cli #1246 — repeated 503  
“No capacity available for model gemini-3.8-flash-\*” with silent retry  
backoff (4s … 24s), 2–5 min total; Claude on the same box: 14s vs 159s
- Forum thread #198333 opened today (Nov 5): “Critical Performance Issue:  
Gemini 3.8 Flash Extremely Slow in Antigravity IDE”

Request: please review 3.8 Flash serving capacity / cluster routing, and  
surface the 503 retries in the UI instead of a silent “Working” state.  
Currently forced to switch models, which defeats the purpose of the Pro plan.

---

<div class="post-metadata">

**Author:** ![Ambati\_Rajendra](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/ambati_rajendra/32/31584_2.png) [@Ambati\_Rajendra](https://discuss.ai.google.dev/u/Ambati_Rajendra)\
**Post date:** [November 11, 2026, 8:10am UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/6 "2026-11-11T08:10:42Z")

</div>

Hi all,

Since you’ve already tried restarting Antigravity, starting a new conversation, and comparing against other models, this doesn’t look like a local machine or network issue—the 2–5 minute stalls in the “Working” state match transient backend capacity limits (HTTP 503 retries) on Gemini 3.8 Flash.

We’re not able to reproduce those multi-minute delays on Gemini 3.8 Flash right now, which points to temporary capacity contention around November 5 rather than a persistent issue. If you run into this slowdown again, here is what you can do right away:

- Open the model selector menu under the conversation prompt box and switch to another available model for your plan (for example, Gemini 4 Argon or Claude Sonnet 5.5 (thinking) on Google AI Pro/Ultra, or another model available in your picker).
- If you switch back to Gemini 3.8 Flash for quick questions or simple edits, keep the thinking level set to Low or Medium in the model selector.

You don’t need to reinstall or clear local app data for this, as model capacity is handled server-side. If you’re still hitting 2–5 minute “Working” delays on Gemini 3.8 Flash today, please reply with your installed Antigravity version and any error output or logs from the session so our team can take a closer look.

---

<div class="post-metadata">

**Author:** ![Marek\_Kopecky](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/marek_kopecky/32/161298_2.png) [@Marek\_Kopecky](https://discuss.ai.google.dev/u/Marek_Kopecky)\
**Post date:** [November 12, 2026, 7:56am UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/7 "2026-11-12T07:56:13Z")

</div>

Hello, I have the same proble, a week after the first report. Gemini Flash 3.8 is totally slow, sometimes it takes 20 minutes to do a simple task. Totally unusable. This started to happen yesterday or day before yesterday yet the situation is worse every hour.

---

<div class="post-metadata">

**Author:** ![BEST\_MOVIES\_CLIPS](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/best_movies_clips/32/168960_2.png) [@BEST\_MOVIES\_CLIPS](https://discuss.ai.google.dev/u/BEST_MOVIES_CLIPS)\
**Post date:** [November 12, 2026, 9:41pm UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/8 "2026-11-12T21:41:55Z")

</div>

13/11/2026

Currently I also facing this same Gemini 3.8 flash model slow response, very frustrated 🥴 taking 1hr + to complete a task , very very slow

Please Fix this As soon as possible!

---

<div class="post-metadata">

**Author:** ![Mikolaj\_R](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/mikolaj_r/32/148883_2.png) [@Mikolaj\_R](https://discuss.ai.google.dev/u/Mikolaj_R)\
**Post date:** [November 13, 2026, 1:29pm UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/9 "2026-11-13T13:29:33Z")

</div>

13/11/2026 ai pro subscription. Extremely slow.

---

<div class="post-metadata">

**Author:** ![A\_John](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/a_john/32/119039_2.png) [@A\_John](https://discuss.ai.google.dev/u/A_John)\
**Post date:** [November 13, 2026, 3:58pm UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/10 "2026-11-13T15:58:43Z")

</div>

Extremely slow, probably starting from yesterday. Even a simple request asking it to say “hello” could take anywhere from tens of seconds to several minutes.

---

<div class="post-metadata">

**Author:** ![rcb](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/rcb/32/165830_2.png) [@rcb](https://discuss.ai.google.dev/u/rcb)\
**Post date:** [November 16, 2026, 4:02pm UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/11 "2026-11-16T16:02:43Z")

</div>

Utterly slow and unreliable. I can even type hello and the thing wont spit back for ages. It seems to be like this for around 2 weeks or so now. I have very good hour(s) then boom nothing. Honestly its so sad to see google fumble this bad. It even happens on hydrogen …

---

<div class="post-metadata">

**Author:** ![Saif\_Ul\_Islam](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/saif_ul_islam/32/171650_2.png) [@Saif\_Ul\_Islam](https://discuss.ai.google.dev/u/Saif_Ul_Islam)\
**Post date:** [November 16, 2026, 5:15pm UTC](https://discuss.ai.google.dev/t/critical-performance-issue-gemini-3-8-flash-extremely-slow-in-antigravity-ide/198333/12 "2026-11-16T17:15:02Z")

</div>

I am having the same issue as well. My Gemini Pro plan’s limit got reset and found out Gemini flash 3.8 to take unexpectedly too long to even making 1 line (in total) code edits.
