[GH-ISSUE #3532] [BUG]: llama runner process has terminated: exit status 2 #2275

Closed
opened 2026-02-22 18:28:57 -05:00 by yindo · 3 comments
Owner

Originally created by @Andyshenjx on GitHub (Mar 25, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3532

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

It can be used normally in the early days, but now it cannot be used, and the models used are DeepSeek32b, MacBook Pro2024 24+1T M4Pro. I can answer questions normally in ollama, but I get this error when I use anythingllm. v1.7.7, macOS 15.4 beta(24E5222f)

Are there known steps to reproduce?

No response

Originally created by @Andyshenjx on GitHub (Mar 25, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3532 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? It can be used normally in the early days, but now it cannot be used, and the models used are DeepSeek32b, MacBook Pro2024 24+1T M4Pro. I can answer questions normally in ollama, but I get this error when I use anythingllm. v1.7.7, macOS 15.4 beta(24E5222f) ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:28:57 -05:00
yindo closed this issue 2026-02-22 18:28:57 -05:00
Author
Owner

@timothycarambat commented on GitHub (Mar 25, 2025):

Seems to be releated to Ollama + memory issues for the model. This thread even has an AnythingLLM user in it with the same issue - so it seems to be the model.

https://github.com/ollama/ollama/issues/8770#issuecomment-2652690708

Depending on the RAM + context window, you may be exceeding mem alloc. TLDR; use a smaller model

@timothycarambat commented on GitHub (Mar 25, 2025): Seems to be releated to Ollama + memory issues for the model. This thread even has an AnythingLLM user in it with the same issue - so it seems to be the model. https://github.com/ollama/ollama/issues/8770#issuecomment-2652690708 Depending on the RAM + context window, you may be exceeding mem alloc. TLDR; use a smaller model
Author
Owner

@Andyshenjx commented on GitHub (Mar 25, 2025):

I can't use it after an update, it used to work fine before, is there any way to modify any parameters to run this model.

@Andyshenjx commented on GitHub (Mar 25, 2025): I can't use it after an update, it used to work fine before, is there any way to modify any parameters to run this model.
Author
Owner

@Shaivpidadi commented on GitHub (Apr 15, 2025):

Facing the same issue on M4 pro, surprisingly works when I run on Linux (using over http, Anything LLM does the same) :/

@Shaivpidadi commented on GitHub (Apr 15, 2025): Facing the same issue on M4 pro, surprisingly works when I run on Linux (using over http, Anything LLM does the same) :/
yindo changed title from [BUG]: llama runner process has terminated: exit status 2 to [GH-ISSUE #3532] [BUG]: llama runner process has terminated: exit status 2 2026-06-05 14:45:36 -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#2275