github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4142] More Quants for command-r-plus Please? #49086

New Issue
Closed
opened 2026-04-28 10:44:06 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 10:44:06 -05:00
Owner
Copy Link

Originally created by @chigkim on GitHub (May 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4142

There are only q2_K, q4_0, q8_0, and fp16 for command-r-plus.
https://ollama.com/library/command-r-plus/tags
Can we have more quants like 0/1/s/m/l of q3, q5, q6 like other models?
Thanks so much!

Originally created by @chigkim on GitHub (May 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4142 There are only q2_K, q4_0, q8_0, and fp16 for command-r-plus. https://ollama.com/library/command-r-plus/tags Can we have more quants like 0/1/s/m/l of q3, q5, q6 like other models? Thanks so much!
GiteaMirror added the model label 2026-04-28 10:44:06 -05:00
GiteaMirror commented 2026-04-28 10:44:08 -05:00
Author
Owner
Copy Link

@taozhiyuai commented on GitHub (May 5, 2024):

import from gguf yourself.

<!-- gh-comment-id:2094656986 --> @taozhiyuai commented on GitHub (May 5, 2024): import from gguf yourself.
GiteaMirror commented 2026-04-28 10:44:08 -05:00
Author
Owner
Copy Link

@chigkim commented on GitHub (May 5, 2024):

I already did even before Ollama had. I'm requesting for other people.

<!-- gh-comment-id:2094777416 --> @chigkim commented on GitHub (May 5, 2024): I already did even before Ollama had. I'm requesting for other people.
GiteaMirror commented 2026-04-28 10:44:09 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 13, 2024):

So you can actually do this pretty easily if you have the non-quantized version checked out either from safetensors or the ollama model. There's instructions in the import doc.

Short answer is:

  1. Create a Modelfile w/ the fp16 model on the FROM line
  2. Run ollama create --quantize q4_K_M test w/ the appropriate quantization level

Command-r is a little long in the tooth, so I'm going to go ahead and close the issue.

<!-- gh-comment-id:2347848934 --> @pdevine commented on GitHub (Sep 13, 2024): So you can actually do this pretty easily if you have the non-quantized version checked out either from safetensors or the ollama model. There's instructions in the [import doc](https://github.com/ollama/ollama/blob/main/docs/import.md#quantizing-a-model). Short answer is: 1. Create a Modelfile w/ the fp16 model on the FROM line 2. Run `ollama create --quantize q4_K_M test` w/ the appropriate quantization level Command-r is a little long in the tooth, so I'm going to go ahead and close the issue.
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#49086
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?