[GH-ISSUE #5455] [BUG]: Intense UI flickering upon sending large mesages #5101

Closed
opened 2026-06-05 14:52:00 -04:00 by yindo · 0 comments
Owner

Originally created by @thedarkestfenix on GitHub (Apr 16, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5455

Originally assigned to: @angelplusultra on GitHub.

How are you running AnythingLLM?

Docker (remote machine)

What happened?

After sending a prompt long enough to trigger the see more option on the prompt's chat buble, the UI starts flickering. When the LLM starts writing the output message the flickering intensifies significantly.

I expected the UI not to flicker.

Are there known steps to reproduce?

Send a prompt that triggers the see more text on the user's text buble. After ollama loads the LLM and it starts thinking the flickering starts. It intensifies significantly when the LLM starts to actually output its answer.

I am running AnythingLLM on a personal computer and exposing it to my tailnet for remote access. The UI is being opened on a mobile Firefox window of a samsung galaxy Tab S9.

This issue has happend to me with or without the phisical keyboard, in landscape and portrait mode, with splitscreen and without splitscreen, on full screen and DEX. I have been unable to find a configuration where it doesn't happen.

I have a screen recording but github did not allow me to upload the .mp4 file. I am willing to send the video through other meens if requested.

LLM Provider & Model (if applicable)

Ollama / Gemma-4-26b-a4b

Embedder Provider & Model (if applicable)

Anything LLM / all-MiniLM-L6-v2

Originally created by @thedarkestfenix on GitHub (Apr 16, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5455 Originally assigned to: @angelplusultra on GitHub. ### How are you running AnythingLLM? Docker (remote machine) ### What happened? After sending a prompt long enough to trigger the see more option on the prompt's chat buble, the UI starts flickering. When the LLM starts writing the output message the flickering intensifies significantly. I expected the UI not to flicker. ### Are there known steps to reproduce? Send a prompt that triggers the see more text on the user's text buble. After ollama loads the LLM and it starts thinking the flickering starts. It intensifies significantly when the LLM starts to actually output its answer. I am running AnythingLLM on a personal computer and exposing it to my tailnet for remote access. The UI is being opened on a mobile Firefox window of a samsung galaxy Tab S9. This issue has happend to me with or without the phisical keyboard, in landscape and portrait mode, with splitscreen and without splitscreen, on full screen and DEX. I have been unable to find a configuration where it doesn't happen. I have a screen recording but github did not allow me to upload the .mp4 file. I am willing to send the video through other meens if requested. ### LLM Provider & Model (if applicable) Ollama / Gemma-4-26b-a4b ### Embedder Provider & Model (if applicable) Anything LLM / all-MiniLM-L6-v2
yindo added the possible buginvestigating labels 2026-06-05 14:52:00 -04:00
yindo closed this issue 2026-06-05 14:52:00 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#5101