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 #207] Floating point exception when running K-Quant model #46595

New Issue
Closed
opened 2026-04-27 23:09:46 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-27 23:09:46 -05:00
Owner
Copy Link

Originally created by @nkoehring on GitHub (Jul 25, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/207

I compiled ollama for Linux and want to use it with already downloaded models. I use models with llama.cpp CPU inference on my laptop, so they are all quantized anyway.

When trying with Mythologic with K-Quant (mythologic-13b.ggmlv3.q5_K_M.bin) method, I get a stack trace:

image

Originally created by @nkoehring on GitHub (Jul 25, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/207 I compiled ollama for Linux and want to use it with already downloaded models. I use models with llama.cpp CPU inference on my laptop, so they are all quantized anyway. When trying with Mythologic with K-Quant (mythologic-13b.ggmlv3.q5_K_M.bin) method, I get a stack trace: ![image](https://github.com/jmorganca/ollama/assets/246402/28f0e195-8c53-4d6c-b7c9-f9b4293602ff)
GiteaMirror added the bug label 2026-04-27 23:09:46 -05:00
GiteaMirror commented 2026-04-27 23:09:52 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Jul 25, 2023):

Thanks for submitting this.

When I run it from main:

./ollama run hi
>>> hi
Error: failed to load model

2023/07/25 11:15:41 routes.go:278: Listening on 127.0.0.1:11434
llama.cpp: loading model from /Users/mchiang/.ollama/models/blobs/sha256:8870d89fb916057519cf1fcb9ca6372d3215b767be524ca314a12ba104213e87
mOK/GԺA0��=Ny�w>�;[�zj#�Y�' should not be 13959180-dimensional
llama_load_model_from_file: failed to load model
[GIN] 2023/07/25 - 11:15:54 | 500 |  3.134388125s |       127.0.0.1 | POST     "/api/generate"
<!-- gh-comment-id:1650044272 --> @mchiang0610 commented on GitHub (Jul 25, 2023): Thanks for submitting this. When I run it from main: ``` ./ollama run hi >>> hi Error: failed to load model ``` ``` 2023/07/25 11:15:41 routes.go:278: Listening on 127.0.0.1:11434 llama.cpp: loading model from /Users/mchiang/.ollama/models/blobs/sha256:8870d89fb916057519cf1fcb9ca6372d3215b767be524ca314a12ba104213e87 mOK/GԺA0��=Ny�w>�;[�zj#�Y�' should not be 13959180-dimensional llama_load_model_from_file: failed to load model [GIN] 2023/07/25 - 11:15:54 | 500 | 3.134388125s | 127.0.0.1 | POST "/api/generate" ```
GiteaMirror commented 2026-04-27 23:09:54 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Jul 25, 2023):

resolved by #209

<!-- gh-comment-id:1650722894 --> @mxyng commented on GitHub (Jul 25, 2023): resolved by #209
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#46595
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?