[GH-ISSUE #4976] Error: pull model manifest: Get #3145

Open
opened 2026-04-12 13:37:26 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @phanikumar96 on GitHub (Jun 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4976

What is the issue?

Ollama is not able to pull the models.

ollama run moon dream

pulling manifest
Error: pull model manifest: Get "https://ollama.com/token?nonce=F_Rh4t6Jrv-EM0eRltrU-Q&scope=repository%!A(MISSING)library%!F(MISSING)moondream%!A(MISSING)pull&service=ollama.com&ts=1718102949": read tcp 10.1.38.47:51154->34.120.132.20:443: read: connection reset by peer

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

No response

Originally created by @phanikumar96 on GitHub (Jun 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4976 ### What is the issue? Ollama is not able to pull the models. ollama run moon dream pulling manifest Error: pull model manifest: Get "https://ollama.com/token?nonce=F_Rh4t6Jrv-EM0eRltrU-Q&scope=repository%!A(MISSING)library%!F(MISSING)moondream%!A(MISSING)pull&service=ollama.com&ts=1718102949": read tcp 10.1.38.47:51154->34.120.132.20:443: read: connection reset by peer ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 13:37:26 -05:00
Author
Owner

@bmizerany commented on GitHub (Jul 11, 2024):

Hi @funnyPhani, Do you happen to still have logs for this in ~/.ollama/logs/server.log?

<!-- gh-comment-id:2223444471 --> @bmizerany commented on GitHub (Jul 11, 2024): Hi @funnyPhani, Do you happen to still have logs for this in `~/.ollama/logs/server.log`?
Author
Owner

@varenc commented on GitHub (Nov 21, 2024):

I had the same problem while trying to run ollama pull llama3.1:8b. Logs looked like this:

time=2024-11-21T14:45:50.689-08:00 level=INFO source=images.go:1020 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3.1/manifests/8b\": dial tcp 104.21.75.227:443: connect: bad file descriptor"
  [GIN] 2024/11/21 - 14:45:50 | 200 |    5.217791ms |       127.0.0.1 | POST     "/api/pull"
  [GIN] 2024/11/21 - 14:45:55 | 200 |      19.292µs |       127.0.0.1 | HEAD     "/"
  time=2024-11-21T14:45:55.119-08:00 level=INFO source=images.go:1020 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3.1/manifests/8b\": dial tcp 104.21.75.227:443: connect: bad file descriptor"
  [GIN] 2024/11/21 - 14:45:55 | 200 |    5.899459ms |       127.0.0.1 | POST     "/api/pull"
  [GIN] 2024/11/21 - 14:46:55 | 200 |          34µs |       127.0.0.1 | HEAD     "/"
  time=2024-11-21T14:46:55.591-08:00 level=INFO source=images.go:1020 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3.1/manifests/8b\": dial tcp 172.67.182.229:443: connect: bad file descriptor"
  [GIN] 2024/11/21 - 14:46:55 | 200 |   10.563084ms |       127.0.0.1 | POST     "/api/pull"

This was while the Ollama GUI program was running in the taskbar. Very strangely if I killed the GUI program and just ran ollama server in one shell and run ollama pull llama3.1:8b in another, it worked just. ¯_(ツ)_/¯

<!-- gh-comment-id:2492515648 --> @varenc commented on GitHub (Nov 21, 2024): I had the same problem while trying to run `ollama pull llama3.1:8b`. Logs looked like this: ``` time=2024-11-21T14:45:50.689-08:00 level=INFO source=images.go:1020 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3.1/manifests/8b\": dial tcp 104.21.75.227:443: connect: bad file descriptor" [GIN] 2024/11/21 - 14:45:50 | 200 | 5.217791ms | 127.0.0.1 | POST "/api/pull" [GIN] 2024/11/21 - 14:45:55 | 200 | 19.292µs | 127.0.0.1 | HEAD "/" time=2024-11-21T14:45:55.119-08:00 level=INFO source=images.go:1020 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3.1/manifests/8b\": dial tcp 104.21.75.227:443: connect: bad file descriptor" [GIN] 2024/11/21 - 14:45:55 | 200 | 5.899459ms | 127.0.0.1 | POST "/api/pull" [GIN] 2024/11/21 - 14:46:55 | 200 | 34µs | 127.0.0.1 | HEAD "/" time=2024-11-21T14:46:55.591-08:00 level=INFO source=images.go:1020 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3.1/manifests/8b\": dial tcp 172.67.182.229:443: connect: bad file descriptor" [GIN] 2024/11/21 - 14:46:55 | 200 | 10.563084ms | 127.0.0.1 | POST "/api/pull" ``` This was while the Ollama GUI program was running in the taskbar. Very strangely if I killed the GUI program and just ran `ollama server` in one shell and run `ollama pull llama3.1:8b` in another, it worked just. ¯\_(ツ)_/¯
Author
Owner

@huyz commented on GitHub (Apr 12, 2025):

For me it turns out that an old ollama server was running but I had already updated the ollama version separately. So I just had to restart the ollama server.

<!-- gh-comment-id:2798737080 --> @huyz commented on GitHub (Apr 12, 2025): For me it turns out that an old ollama server was running but I had already updated the ollama version separately. So I just had to restart the ollama server.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#3145