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 #643] Docs request: quantizations used for Llama models #26044

New Issue
Closed
opened 2026-04-22 01:55:43 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 01:55:43 -05:00
Owner
Copy Link

Originally created by @jamesbraza on GitHub (Sep 29, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/643

https://ollama.ai/library/llama2 is nice that it links the model sources as TheBloke.

Can we add what quantization is used? That way there's more traceability as to what model is being run/downloaded.

Update: I can see from the aliases that it's Q4_0

screenshot of aliases

I think though that's somewhat buried, it would be good to have a more explicit table explaining this.

Originally created by @jamesbraza on GitHub (Sep 29, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/643 https://ollama.ai/library/llama2 is nice that it links the model sources as TheBloke. Can we add what quantization is used? That way there's more traceability as to what model is being run/downloaded. --- Update: I can see from the aliases that it's Q4_0 ![screenshot of aliases](https://github.com/jmorganca/ollama/assets/8990777/44411052-d333-4a9b-b513-4b9eed28394e) I think though that's somewhat buried, it would be good to have a more explicit table explaining this.
GiteaMirror commented 2026-04-22 01:55:43 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Sep 30, 2023):

by default we use q4_0 for the models that we supply (subject to change if you're on the latest tag -- we'll try to pick one that's going to run well for the majority of users).

Now, if you want to specifically pin a version that you want, you can directly use the tags, just like you'd do with containers:

https://ollama.ai/library/llama2/tags

we keep the aliases in there so that it's easier for new users to get started.

<!-- gh-comment-id:1741678452 --> @mchiang0610 commented on GitHub (Sep 30, 2023): by default we use q4_0 for the models that we supply (subject to change if you're on the latest tag -- we'll try to pick one that's going to run well for the majority of users). Now, if you want to specifically pin a version that you want, you can directly use the tags, just like you'd do with containers: https://ollama.ai/library/llama2/tags we keep the aliases in there so that it's easier for new users to get started.
GiteaMirror commented 2026-04-22 01:55:44 -05:00
Author
Owner
Copy Link

@jamesbraza commented on GitHub (Sep 30, 2023):

Thanks for sharing about the Q4_0 model 👍 .

Looking at the llama2:13b tag:

image

I believe this model corresponds with this: https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_0.bin (commit ID 56885c31d70174be02c72ce17904373df1d7830e).

However, I don't see how the commit ID in ollama.ai matches with the Hugging Face commit ID.

How can I go from commit ID to a model in Hugging Face?

<!-- gh-comment-id:1741710962 --> @jamesbraza commented on GitHub (Sep 30, 2023): Thanks for sharing about the Q4_0 model 👍 . --- Looking at the `llama2:13b` tag: <img width="297" alt="image" src="https://github.com/jmorganca/ollama/assets/8990777/348f831d-0d8c-49eb-9369-efe728566d45"> I believe this model corresponds with this: https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_0.bin (commit ID 56885c31d70174be02c72ce17904373df1d7830e). However, I don't see how the commit ID in ollama.ai matches with the Hugging Face commit ID. How can I go from commit ID to a model in Hugging Face?
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#26044
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?