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 #6366] Unable to Pull Model Manifest - "Get https://registry.ollama.ai/v2/library/llama3/manifests/latest: EOF" #3997

New Issue
Closed
opened 2026-04-12 14:52:18 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 14:52:18 -05:00
Owner
Copy Link

Originally created by @uestcxt on GitHub (Aug 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6366

What is the issue?

Description

I am experiencing an issue when trying to pull the llama3 model using the ollama CLI. The process fails with an "EOF" error. I have also tried pulling other models, but the same error occurs.
I have verified that DNS resolution works correctly, as I can resolve the registry.ollama.ai domain:

PS C:\Windows\System32> nslookup registry.ollama.ai
Server:  www.huaweimobilewifi.com
Address:  fe80::1a9e:2cff:fe47:b669

Non-authoritative answer:
Name:    registry.ollama.ai
Addresses:  2606:4700:3036::6815:4be3
           2606:4700:3034::ac43:b6e5
           104.21.75.227

Environment:

  • Ollama Version: 0.3.6
  • Operating System: Windows 11 (Version 10.0.22631, Build 22631)
  • GPU: NVIDIA RTX 4090 Laptop
  • Memory: 64 GB
  • CPU: Intel(R) Core(TM) i9-14900HX, 2200 MHz, 24 cores, 32 logical processors
PS C:\Windows\System32> ollama run llama3
pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3/manifests/latest": EOF
PS C:\Windows\System32> ollama -v
ollama version is 0.3.6

server.log

time=2024-08-15T09:15:43.929+08:00 level=INFO source=images.go:1059 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3/manifests/latest\": EOF"
[GIN] 2024/08/15 - 09:15:43 | 200 |   11.3628421s |       127.0.0.1 | POST     "/api/pull"
[GIN] 2024/08/15 - 09:16:02 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2024/08/15 - 09:16:02 | 404 |            0s |       127.0.0.1 | POST     "/api/show"
time=2024-08-15T09:16:02.628+08:00 level=INFO source=images.go:1059 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3/manifests/latest\": EOF"

It appears that the process is attempting to fetch the manifest but is encountering an EOF error. I have confirmed that my network connection is stable.

Could you please advise on how to resolve this issue?

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.3.6

Originally created by @uestcxt on GitHub (Aug 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6366 ### What is the issue? # Description I am experiencing an issue when trying to pull the llama3 model using the ollama CLI. The process fails with an "EOF" error. I have also tried pulling other models, but the same error occurs. I have verified that DNS resolution works correctly, as I can resolve the registry.ollama.ai domain: ``` PS C:\Windows\System32> nslookup registry.ollama.ai Server: www.huaweimobilewifi.com Address: fe80::1a9e:2cff:fe47:b669 Non-authoritative answer: Name: registry.ollama.ai Addresses: 2606:4700:3036::6815:4be3 2606:4700:3034::ac43:b6e5 104.21.75.227 ``` # Environment: - Ollama Version: 0.3.6 - Operating System: Windows 11 (Version 10.0.22631, Build 22631) - GPU: NVIDIA RTX 4090 Laptop - Memory: 64 GB - CPU: Intel(R) Core(TM) i9-14900HX, 2200 MHz, 24 cores, 32 logical processors ``` PS C:\Windows\System32> ollama run llama3 pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3/manifests/latest": EOF PS C:\Windows\System32> ollama -v ollama version is 0.3.6 ``` # server.log ``` time=2024-08-15T09:15:43.929+08:00 level=INFO source=images.go:1059 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3/manifests/latest\": EOF" [GIN] 2024/08/15 - 09:15:43 | 200 | 11.3628421s | 127.0.0.1 | POST "/api/pull" [GIN] 2024/08/15 - 09:16:02 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/08/15 - 09:16:02 | 404 | 0s | 127.0.0.1 | POST "/api/show" time=2024-08-15T09:16:02.628+08:00 level=INFO source=images.go:1059 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3/manifests/latest\": EOF" ``` It appears that the process is attempting to fetch the manifest but is encountering an EOF error. I have confirmed that my network connection is stable. Could you please advise on how to resolve this issue? ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.6
GiteaMirror added the bugneeds more info labels 2026-04-12 14:52:18 -05:00
GiteaMirror commented 2026-04-12 14:52:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 15, 2024):

This is probably a transient issue, there are reports that Cloudfare has been a bit flaky.

<!-- gh-comment-id:2291014656 --> @rick-github commented on GitHub (Aug 15, 2024): This is probably a transient issue, there are reports that Cloudfare has been a bit flaky.
GiteaMirror commented 2026-04-12 14:52:20 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 1, 2024):

@uestcxt can you try again? are you still seeing the issue?

<!-- gh-comment-id:2323542424 --> @pdevine commented on GitHub (Sep 1, 2024): @uestcxt can you try again? are you still seeing the issue?
GiteaMirror commented 2026-04-12 14:52:20 -05:00
Author
Owner
Copy Link

@R4ZZ3 commented on GitHub (Sep 11, 2024):

I am having similar issues:
image

image
GGUF files from here: https://huggingface.co/mradermacher/Ahma-3B-Instruct-GGUF/tree/main
Original model: https://huggingface.co/Finnish-NLP/Ahma-3B-Instruct

<!-- gh-comment-id:2342666862 --> @R4ZZ3 commented on GitHub (Sep 11, 2024): I am having similar issues: ![image](https://github.com/user-attachments/assets/098462a2-3eec-4aa6-8b9c-52644a71929d) ![image](https://github.com/user-attachments/assets/a3ee5972-832a-4a44-8970-991a115ee861) GGUF files from here: https://huggingface.co/mradermacher/Ahma-3B-Instruct-GGUF/tree/main Original model: https://huggingface.co/Finnish-NLP/Ahma-3B-Instruct
GiteaMirror commented 2026-04-12 14:52:21 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 17, 2024):

@R4ZZ3 I'm not sure how that's related to this issue? I'm assuming you're having problems running a bad GGUF file, but this issue is for ollama pull.

I'm going to go ahead and close this issue though. We can reopen if it keeps happening.

<!-- gh-comment-id:2356265199 --> @pdevine commented on GitHub (Sep 17, 2024): @R4ZZ3 I'm not sure how that's related to this issue? I'm assuming you're having problems running a bad GGUF file, but this issue is for `ollama pull`. I'm going to go ahead and close this issue though. We can reopen if it keeps happening.
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 needs more info
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#3997
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?