mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-11-05 01:07:28 +00:00
[GH-ISSUE #53] Support for Mistral-Large-Instruct-2407-GGUF ? #28
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/ktransformers#28
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
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?
Originally created by @LIUKAI0815 on GitHub (Aug 23, 2024).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/53
Q2、Q3、Q4、Q8、BF16、FP16 ?
@BITcyman commented on GitHub (Aug 23, 2024):
Currently, ktransformers mainly focus on speeding up MoE models. So we support Mixtral-8x7b and Mixtral-8x22b in Release v0.1.2. But Mistral-Large-Instruct is a dense model, which we might not support in the near future.
@LIUKAI0815 commented on GitHub (Aug 28, 2024):
@BITcyman Thanks for replying and looking forward to the new release.
@RWayne93 commented on GitHub (Mar 18, 2026):
I know this is closed but what about large 3 mistralai/Mistral-Large-3-675B-Instruct-2512 this is a MOE model.