[GH-ISSUE #5729] [BUG]: AnythingLLM takes a long time to START to loading the model #5263

Closed
opened 2026-06-05 14:53:00 -04:00 by yindo · 1 comment
Owner

Originally created by @ederstk on GitHub (May 30, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5729

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I don't remember exactly when, but somewhere between updates 1.10 and 1.11, any model I select now takes almost two minutes to START LOADING INTO MEMORY. It's not that the loading process is taking a long time, but there's a huge delay between the prompt sent and when the loading to memory actually begins. After it loads, it works perfectly.
I've tried everything—uninstalling, upgrading, cleaning the registry—nothing works. I've also tried downgrading to 1.10, but it automatically updates to the latest version during installation.

Are there known steps to reproduce?

sendind any prompt

LLM Provider & Model (if applicable)

any model

Embedder Provider & Model (if applicable)

No response

Originally created by @ederstk on GitHub (May 30, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5729 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I don't remember exactly when, but somewhere between updates 1.10 and 1.11, any model I select now takes almost two minutes to START LOADING INTO MEMORY. It's not that the loading process is taking a long time, but there's a huge delay between the prompt sent and when the loading to memory actually begins. After it loads, it works perfectly. I've tried everything—uninstalling, upgrading, cleaning the registry—nothing works. I've also tried downgrading to 1.10, but it automatically updates to the latest version during installation. ### Are there known steps to reproduce? sendind any prompt ### LLM Provider & Model (if applicable) any model ### Embedder Provider & Model (if applicable) _No response_
yindo added the possible bug label 2026-06-05 14:53:00 -04:00
yindo closed this issue 2026-06-05 14:53:00 -04:00
Author
Owner

@timothycarambat commented on GitHub (Jun 1, 2026):

but there's a huge delay between the prompt sent and when the loading to memory actually begins.

The main thing that changed here was upgrade the internal LLM engine (Ollama), but there is nothing we can specifically do to loading the LLM in faster as this is an engine responsibility. It is no mystery Ollama is slow - for this we will actually be migrating to an alternative engine (Llama.cpp) as the default in the near future which is much faster

<!-- gh-comment-id:4593855204 --> @timothycarambat commented on GitHub (Jun 1, 2026): > but there's a huge delay between the prompt sent and when the loading to memory actually begins. The main thing that changed here was upgrade the internal LLM engine (Ollama), but there is nothing we can specifically do to loading the LLM in faster as this is an engine responsibility. It is no mystery Ollama is slow - for this we will actually be migrating to an alternative engine (Llama.cpp) as the default in the near future which is **much** faster
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#5263