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 #6249] ollama run llama3.1 command outputs nonsense #29669

New Issue
Closed
opened 2026-04-22 08:45:20 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 08:45:20 -05:00
Owner
Copy Link

Originally created by @erfan-khalaji on GitHub (Aug 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6249

What is the issue?

After installing Ollama on macOS, I attempted to run the model using the ollama run llama3.1 command. However, when I tried running the model by inputting "hello," it returned what appeared to be random ASCII characters, which didn't make sense. I then used ollama pull llama2 and ollama pull llama3 to see if that would resolve the issue. While ollama run llama3.1 still resulted in nonsensical output, ollama run llama3 and ollama run llama2 worked perfectly. I thought I would share my experience in case it helps someone facing a similar issue.

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

3.1

Originally created by @erfan-khalaji on GitHub (Aug 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6249 ### What is the issue? After installing Ollama on macOS, I attempted to run the model using the `ollama run llama3.1` command. However, when I tried running the model by inputting "hello," it returned what appeared to be random ASCII characters, which didn't make sense. I then used `ollama pull llama2` and `ollama pull llama3` to see if that would resolve the issue. While `ollama run llama3.1` still resulted in nonsensical output, `ollama run llama3` and `ollama run llama2` worked perfectly. I thought I would share my experience in case it helps someone facing a similar issue. ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 3.1
GiteaMirror added the bug label 2026-04-22 08:45:20 -05:00
GiteaMirror commented 2026-04-22 08:45:22 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 8, 2024):

It seems that the Q4_0 quant of llama3.1 doesn't work for a subset of Mac users. What type of Mac are you running? Can you provide server logs?

<!-- gh-comment-id:2276230505 --> @rick-github commented on GitHub (Aug 8, 2024): It seems that the Q4_0 quant of llama3.1 doesn't work for a subset of Mac users. What type of Mac are you running? Can you provide [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues)?
GiteaMirror commented 2026-04-22 08:45:22 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 8, 2024):

If you are running a Mac M1 with 8GB of RAM, the PR https://github.com/ollama/ollama/pull/6260 may fix the issue in the next release.

<!-- gh-comment-id:2276515798 --> @rick-github commented on GitHub (Aug 8, 2024): If you are running a Mac M1 with 8GB of RAM, the PR https://github.com/ollama/ollama/pull/6260 may fix the issue in the next release.
GiteaMirror commented 2026-04-22 08:45:23 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Aug 8, 2024):

Hi @erfan-khalaji , this should be fixed now. You'll need to re-pull llama3.1: ollama pull llama3.1 (sorry!). Let me know if you're still seeing it afterwards.

<!-- gh-comment-id:2276760231 --> @jmorganca commented on GitHub (Aug 8, 2024): Hi @erfan-khalaji , this should be fixed now. You'll need to re-pull `llama3.1`: `ollama pull llama3.1` (sorry!). Let me know if you're still seeing it afterwards.
GiteaMirror commented 2026-04-22 08:45:23 -05:00
Author
Owner
Copy Link

@erfan-khalaji commented on GitHub (Aug 9, 2024):

@rick-github @jmorganca
After re-pulling Llama 3.1, the problem was resolved. Thank you, folks!

<!-- gh-comment-id:2277180661 --> @erfan-khalaji commented on GitHub (Aug 9, 2024): @rick-github @jmorganca After re-pulling Llama 3.1, the problem was resolved. Thank you, folks!
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#29669
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?