Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #3721] [BUG]: Import from GGUF option does nothing. #2395

New Issue
Closed
opened 2026-02-22 18:29:29 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:29:29 -05:00
Owner
Copy Link
Copy Source

Originally created by @ryanpendrick on GitHub (Apr 26, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3721

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

With instance settings>AIprovider>LLM
I have AnythingLLM selected from drop down box as LLM Provider.
Underneath this drop box box is "Import from GGUF" and "Import model from Ollama or Huggingface"
Choosing Import from GGUF and selecting a ~39GB GGUF file results in a loading circle next to the Import text.
And the number "400" slowly flashing underneath.

My drive shows no activity, I've waited 10+ minutes.
Monitored /Users//Library/Application Support/anythingllm-desktop/storage for changes, and nothing.

I also tried to download the GGUF again via the other import option, and again nothing on the drives, nothing on the network.

Choosing an LLM from the list below the import buttons, does fetch and place the model into the Models folder.

Are there known steps to reproduce?

Fresh install.
Mac Sonoma 14.1
LLama 3.3 70b Q_K_M GGUF file.

Originally created by @ryanpendrick on GitHub (Apr 26, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3721 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? With instance settings>AIprovider>LLM I have AnythingLLM selected from drop down box as LLM Provider. Underneath this drop box box is "Import from GGUF" and "Import model from Ollama or Huggingface" Choosing Import from GGUF and selecting a ~39GB GGUF file results in a loading circle next to the Import text. And the number "400" slowly flashing underneath. My drive shows no activity, I've waited 10+ minutes. Monitored /Users/<usr>/Library/Application Support/anythingllm-desktop/storage for changes, and nothing. I also tried to download the GGUF again via the other import option, and again nothing on the drives, nothing on the network. Choosing an LLM from the list below the import buttons, does fetch and place the model into the Models folder. ### Are there known steps to reproduce? Fresh install. Mac Sonoma 14.1 LLama 3.3 70b Q_K_M GGUF file.
yindo added the possible bug label 2026-02-22 18:29:29 -05:00
yindo closed this issue 2026-02-22 18:29:29 -05:00
yindo commented 2026-02-22 18:29:29 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 27, 2025):

Can you see any logs? This is a big model, but still should not be a huge issues. That being said this import process is the same as running ollama create - which copies the model as well as does some other tasks for it to be loadable into the model.

Since the model is LLama3.3 70B you could just put ollama run llama3.3 into that import input field and it would pull the same model from the registry. Either way, without any logs it would be hard to know if this is system, app, or perms related

@timothycarambat commented on GitHub (Apr 27, 2025): Can you see any [logs](https://docs.anythingllm.com/installation-desktop/debug#general-debugging)? This is a big model, but still should not be a huge issues. That being said this import process is the same as running `ollama create` - which copies the model as well as does some other tasks for it to be loadable into the model. Since the model is LLama3.3 70B you could just put `ollama run llama3.3` into that import input field and it would pull the same model from the registry. Either way, without any logs it would be hard to know if this is system, app, or perms related
yindo commented 2026-02-22 18:29:29 -05:00
Author
Owner
Copy Link
Copy Source

@OKTAYMERCAN commented on GitHub (Apr 29, 2025):

Image

The same thing happens to me. No matter what type of model I add, it ends up like in the screenshot — it shows a 400 error and nothing happens. It's really frustrating.

@OKTAYMERCAN commented on GitHub (Apr 29, 2025): <img width="509" alt="Image" src="https://github.com/user-attachments/assets/a76cb768-b5b1-4469-86cf-87d28d7c79b2" /> The same thing happens to me. No matter what type of model I add, it ends up like in the screenshot — it shows a 400 error and nothing happens. It's really frustrating.
yindo changed title from [BUG]: Import from GGUF option does nothing. to [GH-ISSUE #3721] [BUG]: Import from GGUF option does nothing. 2026-06-05 14:46:19 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label possible bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2395
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?