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 #4621] phi3-medium-128k wrong number of tensors #64940

New Issue
Closed
opened 2026-05-03 19:20:12 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 19:20:12 -05:00
Owner
Copy Link

Originally created by @EthanGraber on GitHub (May 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4621

What is the issue?

I'm getting the following error when testing the new 128k versions of phi3-medium:

$ ollama run phi3:14b-medium-128k-instruct-q4_0
Error: llama runner process has terminated: signal: abort trap error:done_getting_tensors: wrong number of tensors; expected 245, got 243

$ ollama -v                                    
ollama version is 0.1.38

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.38

Originally created by @EthanGraber on GitHub (May 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4621 ### What is the issue? I'm getting the following error when testing the new 128k versions of phi3-medium: ```sh $ ollama run phi3:14b-medium-128k-instruct-q4_0 Error: llama runner process has terminated: signal: abort trap error:done_getting_tensors: wrong number of tensors; expected 245, got 243 ``` ```sh $ ollama -v ollama version is 0.1.38 ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.38
GiteaMirror added the bug label 2026-05-03 19:20:12 -05:00
GiteaMirror commented 2026-05-03 19:20:17 -05:00
Author
Owner
Copy Link

@thinkverse commented on GitHub (May 24, 2024):

0.1.38 doesn't support those versions of phi3. llama.cpp just added support for it a few days ago so you'll have to wait for Ollama 0.1.39 which has the updated backend. It is currently in pre-release, https://github.com/ollama/ollama/releases/tag/v0.1.39, so it should released soon I think. 👍

I'd suggest either waiting for that or testing with the pre-release version if you have the chance and see if the issue persists.

<!-- gh-comment-id:2130423741 --> @thinkverse commented on GitHub (May 24, 2024): 0.1.38 doesn't support those versions of phi3. llama.cpp just added support for it a few days ago so you'll have to wait for Ollama 0.1.39 which has the updated backend. It is currently in pre-release, https://github.com/ollama/ollama/releases/tag/v0.1.39, so it should released soon I think. 👍 I'd suggest either waiting for that or testing with the pre-release version if you have the chance and see if the issue persists.
GiteaMirror commented 2026-05-03 19:20:18 -05:00
Author
Owner
Copy Link

@EthanGraber commented on GitHub (May 24, 2024):

Oh whoops. Yeah, it works perfectly on v0.1.39. My bad!

<!-- gh-comment-id:2130431093 --> @EthanGraber commented on GitHub (May 24, 2024): Oh whoops. Yeah, it works perfectly on v0.1.39. My bad!
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#64940
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?