[GH-ISSUE #7698] Pulling llama3.1 from ollama results in json error #4915

Closed
opened 2026-04-12 15:58:24 -05:00 by GiteaMirror · 7 comments
Owner

Originally created by @dkarthicks27 on GitHub (Nov 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7698

What is the issue?

When I try to run the following command:
ollama pull llama3.1

I get the following issue:
Error: invalid character '}' looking for beginning of object key string.

OS: Mac M1 (14.1.1)
ollama version: 0.3.12

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.3.12

Originally created by @dkarthicks27 on GitHub (Nov 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7698 ### What is the issue? When I try to run the following command: `ollama pull llama3.1` I get the following issue: `Error: invalid character '}' looking for beginning of object key string`. OS: Mac M1 (14.1.1) ollama version: 0.3.12 ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.3.12
GiteaMirror added the bug label 2026-04-12 15:58:24 -05:00
Author
Owner

@arbusam commented on GitHub (Nov 16, 2024):

Have you tried updating to the newest version and seeing if this still happens? I'm on an M2 Mac mini on a newer version and this doesn't happen to me.

<!-- gh-comment-id:2480487810 --> @arbusam commented on GitHub (Nov 16, 2024): Have you tried updating to the newest version and seeing if this still happens? I'm on an M2 Mac mini on a newer version and this doesn't happen to me.
Author
Owner

@rick-github commented on GitHub (Nov 17, 2024):

Have you successfully pulled models before? What's the output of the following command:

curl -D - https://registry.ollama.ai/v2/library/llama3.1/manifests/latest
<!-- gh-comment-id:2481336874 --> @rick-github commented on GitHub (Nov 17, 2024): Have you successfully pulled models before? What's the output of the following command: ```console curl -D - https://registry.ollama.ai/v2/library/llama3.1/manifests/latest ```
Author
Owner

@dkarthicks27 commented on GitHub (Nov 17, 2024):

Have you tried updating to the newest version and seeing if this still happens? I'm on an M2 Mac mini on a newer version and this doesn't happen to me.

I have tried other models, like mistral and gemma, and it does work. Manifest is pulled successfully, I observed this specific to llama3.1

<!-- gh-comment-id:2481341889 --> @dkarthicks27 commented on GitHub (Nov 17, 2024): > Have you tried updating to the newest version and seeing if this still happens? I'm on an M2 Mac mini on a newer version and this doesn't happen to me. I have tried other models, like mistral and gemma, and it does work. Manifest is pulled successfully, I observed this specific to llama3.1
Author
Owner

@rick-github commented on GitHub (Nov 17, 2024):

Does this work any better:

ollama pull llama3.1:8b-instruct-q4_0
<!-- gh-comment-id:2481352667 --> @rick-github commented on GitHub (Nov 17, 2024): Does this work any better: ``` ollama pull llama3.1:8b-instruct-q4_0 ```
Author
Owner

@dkarthicks27 commented on GitHub (Nov 17, 2024):

Have you successfully pulled models before? What's the output of the following command:

curl -D - https://registry.ollama.ai/v2/library/llama3.1/manifests/latest

Hey @rick-github, I find it surprising, as I tried pulling the model, with a different wifi, and this time around it works, without any issues.

What could be the underlying issue, as I am not able replicate the same issue. While the other day, it happened, even after updating ollama using pip, and reoccurred multiple times. But today its able to pull.

<!-- gh-comment-id:2481352929 --> @dkarthicks27 commented on GitHub (Nov 17, 2024): > Have you successfully pulled models before? What's the output of the following command: > > ``` > curl -D - https://registry.ollama.ai/v2/library/llama3.1/manifests/latest > ``` Hey @rick-github, I find it surprising, as I tried pulling the model, with a different wifi, and this time around it works, without any issues. What could be the underlying issue, as I am not able replicate the same issue. While the other day, it happened, even after updating ollama using pip, and reoccurred multiple times. But today its able to pull.
Author
Owner

@dkarthicks27 commented on GitHub (Nov 17, 2024):

Does this work any better:

ollama pull llama3.1:8b-instruct-q4_0

This didn't work the other day, I tried this, but worked with

ollama pull llama3.2:3b-instruct-fp16

<!-- gh-comment-id:2481354284 --> @dkarthicks27 commented on GitHub (Nov 17, 2024): > Does this work any better: > > ``` > ollama pull llama3.1:8b-instruct-q4_0 > ``` This didn't work the other day, I tried this, but worked with `ollama pull llama3.2:3b-instruct-fp16`
Author
Owner

@rick-github commented on GitHub (Nov 17, 2024):

Looks like a transient issue, no repro.

<!-- gh-comment-id:2481395559 --> @rick-github commented on GitHub (Nov 17, 2024): Looks like a transient issue, no repro.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#4915