github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3660] Exception using command-r-plus:104b-q4_0 #2256

New Issue
Closed
opened 2026-04-12 12:31:48 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 12:31:48 -05:00
Owner
Copy Link

Originally created by @mehdiataei on GitHub (Apr 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3660

What is the issue?

Ollama: exception done_getting_tensors: wrong number of tensors; expected 642, got 514

What did you expect to see?

No response

Steps to reproduce

No response

Are there any recent changes that introduced the issue?

No response

OS

No response

Architecture

No response

Platform

No response

Ollama version

No response

GPU

No response

GPU info

No response

CPU

No response

Other software

No response

Originally created by @mehdiataei on GitHub (Apr 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3660 ### What is the issue? Ollama: exception done_getting_tensors: wrong number of tensors; expected 642, got 514 ### What did you expect to see? _No response_ ### Steps to reproduce _No response_ ### Are there any recent changes that introduced the issue? _No response_ ### OS _No response_ ### Architecture _No response_ ### Platform _No response_ ### Ollama version _No response_ ### GPU _No response_ ### GPU info _No response_ ### CPU _No response_ ### Other software _No response_
GiteaMirror added the bug label 2026-04-12 12:31:48 -05:00
GiteaMirror commented 2026-04-12 12:31:49 -05:00
Author
Owner
Copy Link

@park commented on GitHub (Apr 16, 2024):

Same issue here on docker v0.1.32 @Ubuntu w/ 5950x + NVIDIA 2080Ti 22GB + 128GB memory.

<!-- gh-comment-id:2058131824 --> @park commented on GitHub (Apr 16, 2024): Same issue here on docker v0.1.32 @Ubuntu w/ 5950x + NVIDIA 2080Ti 22GB + 128GB memory.
GiteaMirror commented 2026-04-12 12:31:49 -05:00
Author
Owner
Copy Link

@madroidmaq commented on GitHub (Apr 16, 2024):

The problem was also encountered on the Apple M3 Max, which reported the following error:

ollama run command-r-plus
pulling manifest
pulling 503c8cac166f... 100% ▕███████████████████████████████▏  59 GB
pulling f0624a2393a5... 100% ▕███████████████████████████████▏  13 KB
pulling 42499e38acdf... 100% ▕███████████████████████████████▏  270 B
pulling 36b9655abe6a... 100% ▕███████████████████████████████▏   81 B
pulling 748dd5320e31... 100% ▕███████████████████████████████▏  493 B
verifying sha256 digest
writing manifest
removing any unused layers
success
Error: exception done_getting_tensors: wrong number of tensors; expected 642, got 514

PS：ollama version is 0.1.31

<!-- gh-comment-id:2058162945 --> @madroidmaq commented on GitHub (Apr 16, 2024): The problem was also encountered on the Apple M3 Max, which reported the following error: ``` ollama run command-r-plus pulling manifest pulling 503c8cac166f... 100% ▕███████████████████████████████▏ 59 GB pulling f0624a2393a5... 100% ▕███████████████████████████████▏ 13 KB pulling 42499e38acdf... 100% ▕███████████████████████████████▏ 270 B pulling 36b9655abe6a... 100% ▕███████████████████████████████▏ 81 B pulling 748dd5320e31... 100% ▕███████████████████████████████▏ 493 B verifying sha256 digest writing manifest removing any unused layers success Error: exception done_getting_tensors: wrong number of tensors; expected 642, got 514 ``` PS：ollama version is 0.1.31
GiteaMirror commented 2026-04-12 12:31:49 -05:00
Author
Owner
Copy Link

@madroidmaq commented on GitHub (Apr 16, 2024):

ollama version is 0.1.32 is work for me

<!-- gh-comment-id:2058281411 --> @madroidmaq commented on GitHub (Apr 16, 2024): ollama version is 0.1.32 is work for me
GiteaMirror commented 2026-04-12 12:31:50 -05:00
Author
Owner
Copy Link

@lunyang commented on GitHub (Apr 16, 2024):

Try to install curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.1.32 sh, it woks.

<!-- gh-comment-id:2058783568 --> @lunyang commented on GitHub (Apr 16, 2024): Try to install `curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.1.32 sh`, it woks.
GiteaMirror commented 2026-04-12 12:31:50 -05:00
Author
Owner
Copy Link

@ai-Ev1lC0rP commented on GitHub (Apr 16, 2024):

I had the same issue on MBP M2 Max 64GB. Candidly i'm on pre-release OS 14.5 Sonoma.
Never the less.
I just pulled the latest from the ollama site and it's still on version 1.31, 1.32 is pre-release so you will need to head on over to the releases page.

But i can confirm @lunyang is right. It's resolved in pre-release version 1.32 as indicated in the docs.

on version 0.1.31

ollama -v
ollama version is 0.1.31
Warning: client version is 0.0.0
ollama run command-r-plus
Error: exception done_getting_tensors: wrong number of tensors; expected 642, got 514

working on version 0.1.32 %


ollama run command-r-plus
>>> hello how are you?
I  ^C

>>> /bye
ollama -v     
ollama version is 0.1.32
Warning: client version is 0.0.0

I think this should be marked as resolved no-issue.

**As a Note.....This model is huge and i'm not expecting it to work well if at all on my m2 Max or my 4090TI/64 gigs of ram. @park with the 2080 and all the DDRegularram. . . . I think you might be dreaming thinking that will run but i've been wrong many times before. ;) I have a 1TB of DDR4 in a machine WITHOUT a gpu and run dual massive intel cpu's and.... cpu + ddr3/4/5 isnt the same and doesnt translate 1:1

Good luck everyone!

<!-- gh-comment-id:2059378715 --> @ai-Ev1lC0rP commented on GitHub (Apr 16, 2024): I had the same issue on MBP M2 Max 64GB. Candidly i'm on pre-release OS 14.5 Sonoma. Never the less. I just pulled the latest from the ollama site and it's still on version 1.31, 1.32 is pre-release so you will need to head on over to the releases page. But i can confirm @lunyang is right. It's resolved in pre-release version 1.32 as indicated in the docs. ### on version 0.1.31 ``` ollama -v ollama version is 0.1.31 Warning: client version is 0.0.0 ollama run command-r-plus Error: exception done_getting_tensors: wrong number of tensors; expected 642, got 514 ``` ### working on version 0.1.32 % ``` ollama run command-r-plus >>> hello how are you? I ^C >>> /bye ollama -v ollama version is 0.1.32 Warning: client version is 0.0.0 ``` I think this should be marked as resolved no-issue. **As a Note.....This model is *huge* and i'm not expecting it to work well if at all on my m2 Max or my 4090TI/64 gigs of ram. @park with the 2080 and all the DDRegularram. . . . I think you might be dreaming thinking that will run but i've been wrong many times before. ;) I have a 1TB of DDR4 in a machine WITHOUT a gpu and run dual massive intel cpu's and.... cpu + ddr3/4/5 isnt the same and doesnt translate 1:1 Good luck everyone!
GiteaMirror commented 2026-04-12 12:31:51 -05:00
Author
Owner
Copy Link

@park commented on GitHub (Apr 17, 2024):

I can confirm that after removing and re-pulling the docker container v0.1.32, and it works alright. The speed is very slow though.

I guess this issue is resolved.

<!-- gh-comment-id:2060118484 --> @park commented on GitHub (Apr 17, 2024): I can confirm that after removing and re-pulling the docker container v0.1.32, and it works alright. The speed is very slow though. I guess this issue is resolved.
GiteaMirror commented 2026-04-12 12:31:52 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Apr 17, 2024):

Hi there, command-r-plus requires 0.1.32! Sorry the error message for this isn't more obvious - will improve this in an upcoming release

<!-- gh-comment-id:2060123307 --> @jmorganca commented on GitHub (Apr 17, 2024): Hi there, command-r-plus requires 0.1.32! Sorry the error message for this isn't more obvious - will improve this in an upcoming release
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 bug
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#2256
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?