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 #7901] Error: max retries exceeded: unexpected EOF #30815

New Issue
Closed
opened 2026-04-22 10:45:10 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-22 10:45:10 -05:00
Owner
Copy Link

Originally created by @szzhh on GitHub (Dec 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7901

What is the issue?

When I pull the llama3.1:405b model, ' Error: max retries exceeded: unexpected EOF ' often appears. But usually, I can continue downloading instead of re-downloading. But I encountered a problem yesterday. I downloaded more than 200g of the model, but after the error, I had to re-download the command, and the model's ID and size also changed. I have encountered this problem before, as shown in the figure below. I don't know why I encounter such a problem. Is there any way I can continue downloading?
3
1
2

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.4.6

Originally created by @szzhh on GitHub (Dec 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7901 ### What is the issue? When I pull the llama3.1:405b model, ' Error: max retries exceeded: unexpected EOF ' often appears. But usually, I can continue downloading instead of re-downloading. But I encountered a problem yesterday. I downloaded more than 200g of the model, but after the error, I had to re-download the command, and the model's ID and size also changed. I have encountered this problem before, as shown in the figure below. I don't know why I encounter such a problem. Is there any way I can continue downloading? ![3](https://github.com/user-attachments/assets/d60bce03-ebbf-4741-8fcc-f803892e71a6) ![1](https://github.com/user-attachments/assets/f13af8bc-d382-46c6-833f-fe03ff0ed514) ![2](https://github.com/user-attachments/assets/a364694f-90dc-4e1c-ab06-0388ad2d219c) ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.4.6
GiteaMirror added the bug label 2026-04-22 10:45:10 -05:00
GiteaMirror commented 2026-04-22 10:45:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 1, 2024):

The default quant has been changed from q4_0 to q4_K_M. You might be able to resume the download by pulling llama3.1:405b-instruct-q4_0.

<!-- gh-comment-id:2509653413 --> @rick-github commented on GitHub (Dec 1, 2024): The default quant has been changed from q4_0 to q4_K_M. You might be able to resume the download by pulling llama3.1:405b-instruct-q4_0.
GiteaMirror commented 2026-04-22 10:45:12 -05:00
Author
Owner
Copy Link

@szzhh commented on GitHub (Dec 1, 2024):

The default quant has been changed from q4_0 to q4_K_M. You might be able to resume the download by pulling llama3.1:405b-instruct-q4_0.

Thank you for your reply, I can continue downloading now. By the way, may I ask if there have been any significant changes between the modified model and the original model.

<!-- gh-comment-id:2509661787 --> @szzhh commented on GitHub (Dec 1, 2024): > The default quant has been changed from q4_0 to q4_K_M. You might be able to resume the download by pulling llama3.1:405b-instruct-q4_0. Thank you for your reply, I can continue downloading now. By the way, may I ask if there have been any significant changes between the modified model and the original model.
GiteaMirror commented 2026-04-22 10:45:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 1, 2024):

https://github.com/ollama/ollama/issues/5425

<!-- gh-comment-id:2509665531 --> @rick-github commented on GitHub (Dec 1, 2024): https://github.com/ollama/ollama/issues/5425
GiteaMirror commented 2026-04-22 10:45:13 -05:00
Author
Owner
Copy Link

@szzhh commented on GitHub (Dec 1, 2024):

thank you 

szh
@.***

---Original---
From: @.>
Date: Sun, Dec 1, 2024 17:58 PM
To: @.>;
Cc: "Sun @.@.>;
Subject: Re: [ollama/ollama] Error: max retries exceeded: unexpected EOF(Issue #7901)

#5425

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: @.***>

<!-- gh-comment-id:2509667908 --> @szzhh commented on GitHub (Dec 1, 2024): thank you&nbsp; szh ***@***.*** ---Original--- From: ***@***.***&gt; Date: Sun, Dec 1, 2024 17:58 PM To: ***@***.***&gt;; Cc: "Sun ***@***.******@***.***&gt;; Subject: Re: [ollama/ollama] Error: max retries exceeded: unexpected EOF(Issue #7901) #5425 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***&gt;
GiteaMirror commented 2026-04-22 10:45:13 -05:00
Author
Owner
Copy Link

@szzhh commented on GitHub (Dec 2, 2024):

#5425

Hello, I would like to ask why the GPU memory usage keeps showing 0MB during model inference.
4

<!-- gh-comment-id:2510548737 --> @szzhh commented on GitHub (Dec 2, 2024): > #5425 Hello, I would like to ask why the GPU memory usage keeps showing 0MB during model inference. ![4](https://github.com/user-attachments/assets/efc3b19e-96ed-4c62-8040-0c3b88bcbffd)
GiteaMirror commented 2026-04-22 10:45:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 2, 2024):

Server logs would aid in debugging.

<!-- gh-comment-id:2510999088 --> @rick-github commented on GitHub (Dec 2, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) would aid in debugging.
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#30815
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?