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 #1925] [Failed to load model] under Native models #1248

New Issue
Closed
opened 2026-02-22 18:23:55 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:23:55 -05:00
Owner
Copy Link
Copy Source

Originally created by @ghost on GitHub (Jul 23, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1925

I have my own fine-tuned model and i have placed in the downloaded folder and can be detected by Native LLM selection. But as i prompt something, it crashes by saying [Failed to load model]. Need help on this.

Originally created by @ghost on GitHub (Jul 23, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1925 I have my own fine-tuned model and i have placed in the downloaded folder and can be detected by Native LLM selection. But as i prompt something, it crashes by saying [Failed to load model]. Need help on this.
yindo closed this issue 2026-02-22 18:23:55 -05:00
yindo commented 2026-02-22 18:23:55 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jul 23, 2024):

There is not enough information to possibly assist here. What kind of model did you load? LoRA? Q_?
Second, that version of llama-cpp will not bind to your GPU most likely and inference will be slow unless on a unified memory system (M1,M2,M3).

Lastly, we are going to be removing the built-in native runner because of issues like this and the lack of GPU support, we will be reinventing technology that is better handled by other local LLM runners like Ollama, LMStudio, or LocalAI. Whatever your model is, it will likely be easier to run and get inferencing via Ollama and using that connection in AnythingLLM

@timothycarambat commented on GitHub (Jul 23, 2024): There is not enough information to possibly assist here. What kind of model did you load? LoRA? Q_? Second, that version of llama-cpp will _not_ bind to your GPU most likely and inference will be slow unless on a unified memory system (M1,M2,M3). Lastly, we are going to be removing the built-in native runner because of issues like this and the lack of GPU support, we will be reinventing technology that is better handled by other local LLM runners like Ollama, LMStudio, or LocalAI. Whatever your model is, it will likely be easier to run and get inferencing via Ollama and using that connection in AnythingLLM
yindo changed title from [Failed to load model] under Native models to [GH-ISSUE #1925] [Failed to load model] under Native models 2026-06-05 14:39:44 -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
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#1248
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?