github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 05:31:43 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3175] Run Mixtral-8x7B on Consumer Hardware with Expert Offloading #1955

New Issue
Closed
opened 2026-04-12 12:06:20 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 12:06:20 -05:00
Owner
Copy Link

Originally created by @arjunkrishna on GitHub (Mar 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3175

What are you trying to do?

mixtral:8x7B on rtx 3090 runs slow due to size issue.

How should we solve this?

in this article it says we can offload some experts to make it run faster.
https://kaitchup.substack.com/p/run-mixtral-8x7b-on-consumer-hardware
If you have already implemented this in ollama, then I apologize.

What is the impact of not solving this?

mixtral may run faster on rtx 3090.

Anything else?

https://github.com/dvmazur/mixtral-offloading

No response

Originally created by @arjunkrishna on GitHub (Mar 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3175 ### What are you trying to do? mixtral:8x7B on rtx 3090 runs slow due to size issue. ### How should we solve this? in this article it says we can offload some experts to make it run faster. https://kaitchup.substack.com/p/run-mixtral-8x7b-on-consumer-hardware If you have already implemented this in ollama, then I apologize. ### What is the impact of not solving this? mixtral may run faster on rtx 3090. ### Anything else? https://github.com/dvmazur/mixtral-offloading _No response_
GiteaMirror commented 2026-04-12 12:06:22 -05:00
Author
Owner
Copy Link

@arjunkrishna commented on GitHub (Mar 16, 2024):

ah... I see this on another issue with mixtral slowness on 3090. I am closing this as it is a duplicate of https://github.com/ollama/ollama/issues/1556 I am going to try mixtral:8x7b-instruct-v0.1-q2_K version instead

<!-- gh-comment-id:2000929885 --> @arjunkrishna commented on GitHub (Mar 16, 2024): ah... I see this on another issue with mixtral slowness on 3090. I am closing this as it is a duplicate of https://github.com/ollama/ollama/issues/1556 I am going to try mixtral:8x7b-instruct-v0.1-q2_K version instead
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#1955
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?