Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-21 01:25:28 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #4113] Add Qualcomm AI Hub supported LLMs to AnythingLLM desktop #2619

New Issue
Closed
opened 2026-02-22 18:30:29 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:30:29 -05:00
Owner
Copy Link
Copy Source

Originally created by @axcpy08 on GitHub (Jul 9, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4113

I've successfully run the default Llama 3.2 and 3.1 models in AnythingLLM desktop on a Qualcomm X Elite laptop.

I noticed that Qualcomm AI Hub has released several Llama-based models (TAIDE, SEALION), and I’d like to integrate them into AnythingLLM desktop application.

Specifically:

  1. Can these models be added manually?
  2. Are there any guidelines available to support this integration?
  3. Are any code changes required to make these models compatible with AnythingLLM?

Any insights or references would be greatly appreciated. Thank you.

Originally created by @axcpy08 on GitHub (Jul 9, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4113 I've successfully run the default Llama 3.2 and 3.1 models in AnythingLLM desktop on a Qualcomm X Elite laptop. I noticed that Qualcomm AI Hub has released several Llama-based models (TAIDE, SEALION), and I’d like to integrate them into AnythingLLM desktop application. Specifically: 1. Can these models be added manually? 2. Are there any guidelines available to support this integration? 3. Are any code changes required to make these models compatible with AnythingLLM? Any insights or references would be greatly appreciated. Thank you.
yindo closed this issue 2026-02-22 18:30:29 -05:00
yindo commented 2026-02-22 18:30:29 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jul 9, 2025):

You can download them as a zip (if available) and use them in the current NPU engine. However the reason all the models do not exist is because models like LLama TAIDE cannot be exported as zip and instead we have to manually export them on a large to Snapdragon X Elite compatibility.

The template and such for these models should work as is, but the reason for the model limitation is that it takes about 4 hours per mode to export and its a very tedious process. Its not something we recommend doing manually since it is very involved. In theory if you get it exported with its .bin and genie_config.json then having the folder in the model/QNN folder in the application storage it should load fine

@timothycarambat commented on GitHub (Jul 9, 2025): You _can_ download them as a zip (if available) and use them in the current NPU engine. However the reason all the models do not exist is because models like LLama TAIDE cannot be exported as zip and instead we have to manually export them on a large to Snapdragon X Elite compatibility. The template and such for these models should work as is, but the reason for the model limitation is that it takes about 4 hours per mode to export and its a very tedious process. Its not something we recommend doing manually since it is very involved. In theory if you get it exported with its `.bin` and `genie_config.json` then having the folder in the model/QNN folder in the application storage it should load fine
yindo changed title from Add Qualcomm AI Hub supported LLMs to AnythingLLM desktop to [GH-ISSUE #4113] Add Qualcomm AI Hub supported LLMs to AnythingLLM desktop 2026-06-05 14:47:35 -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#2619
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?