github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7054] Support for Zamba2 #4478

New Issue
Open
opened 2026-04-12 15:24:20 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 15:24:20 -05:00
Owner
Copy Link

Originally created by @hg0428 on GitHub (Oct 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7054

Zamba2 is a really cool model that uses a hybrid Mamba-Transformer system.
https://huggingface.co/Zyphra/Zamba2-2.7B
https://www.zyphra.com/post/zamba2-small

I have been wanting to use this for a while and I would love if ollama could add this model soon.

Originally created by @hg0428 on GitHub (Oct 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7054 Zamba2 is a really cool model that uses a hybrid Mamba-Transformer system. https://huggingface.co/Zyphra/Zamba2-2.7B https://www.zyphra.com/post/zamba2-small I have been wanting to use this for a while and I would love if ollama could add this model soon.
GiteaMirror added the model label 2026-04-12 15:24:20 -05:00
GiteaMirror commented 2026-04-12 15:24:21 -05:00
Author
Owner
Copy Link

@hg0428 commented on GitHub (Oct 1, 2024):

I think it would also be a good idea to add support for Nvidia's Mamba-hybrid models: https://huggingface.co/nvidia/mamba2-hybrid-8b-3t-128k

<!-- gh-comment-id:2384666516 --> @hg0428 commented on GitHub (Oct 1, 2024): I think it would also be a good idea to add support for Nvidia's Mamba-hybrid models: https://huggingface.co/nvidia/mamba2-hybrid-8b-3t-128k
GiteaMirror commented 2026-04-12 15:24:23 -05:00
Author
Owner
Copy Link

@hg0428 commented on GitHub (Oct 1, 2024):

And maybe Zamba1.
All of these use a Mamba-transformer hybrid architecture so you may be able to add them all together.

<!-- gh-comment-id:2384667484 --> @hg0428 commented on GitHub (Oct 1, 2024): And maybe Zamba1. All of these use a Mamba-transformer hybrid architecture so you may be able to add them all together.
GiteaMirror commented 2026-04-12 15:24:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 1, 2024):

Needs hybrid support in llama.cpp: https://github.com/ggerganov/llama.cpp/pull/7531

<!-- gh-comment-id:2384673230 --> @rick-github commented on GitHub (Oct 1, 2024): Needs hybrid support in llama.cpp: https://github.com/ggerganov/llama.cpp/pull/7531
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 model
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#4478
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?