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 #9621] Error: pull model manifest on MacOS #6278

New Issue
Closed
opened 2026-04-12 17:42:06 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 17:42:06 -05:00
Owner
Copy Link

Originally created by @georgemac-labs on GitHub (Mar 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9621

What is the issue?

Since today, ollama run does not work for models that I haven't already downloaded

Examples:

$ ollama run qwq:32b
pulling manifest 
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/qwq/manifests/32b": dial tcp 104.21.75.227:443: connect: bad file descriptor

$ollama run phi4-mini
pulling manifest 
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/phi4-mini/manifests/latest": dial tcp 104.21.75.227:443: connect: bad file descriptor

However, curl is able to fetch these URLs just fine

$ curl https://registry.ollama.ai/v2/library/qwq/manifests/32b
{"schemaVersion":2,"mediaType":"application/vnd.docker.distribution.manifest.v2+json","config":{"mediaType":"application/vnd.docker.container.image.v1+json","digest":"sha256:6a8faa2fb8b028e782399922ea8eef06b55ec45e2dea1e46642b4326af2020f8","size":488},"layers":[{"mediaType":"application/vnd.ollama.image.model","digest":"sha256:c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb","size":19851336256},{"mediaType":"application/vnd.ollama.image.template","digest":"sha256:41190096a061d4e37207f28e5306f56f55b451127a23df8e38b82dca8947cb98","size":1231},{"mediaType":"application/vnd.ollama.image.license","digest":"sha256:d18a5cc71b84bc4af394a31116bd3932b42241de70c77d2b76d69a314ec8aa12","size":11338},{"mediaType":"application/vnd.ollama.image.params","digest":"sha256:4afe5edfdb51c6d15bdb8124bd38ea5642bb6732ae3fd09abe0fefa1ace25caa","size":77}]}%

What I'm seeing is the same behaviour described in https://github.com/ollama/ollama/issues/7495 – if I close the menu bar app and run ollama serve, the error does not appear. However, in this case, it wants to redownload the model from scratch (I already had 90%).

Models that are already downloaded work as normal.

This is on MacOS 13.7.2 and I have 100s of GB of storage free.

Relevant log output

[GIN] 2025/03/10 - 14:05:07 | 200 |      60.291µs |       127.0.0.1 | GET      "/api/version"
2025/03/10 14:05:39 routes.go:1215: INFO server config env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/john/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]"
time=2025-03-10T14:05:39.601+07:00 level=INFO source=images.go:432 msg="total blobs: 84"
time=2025-03-10T14:05:39.602+07:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-03-10T14:05:39.603+07:00 level=INFO source=routes.go:1277 msg="Listening on 127.0.0.1:11434 (version 0.5.13)"
time=2025-03-10T14:05:39.671+07:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=metal variant="" compute="" driver=0.0 name="" total="32.0 GiB" available="32.0 GiB"
update check failed - TypeError: fetch failed
[GIN] 2025/03/10 - 14:05:39 | 200 |      29.584µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/03/10 - 14:05:39 | 404 |    1.881209ms |       127.0.0.1 | POST     "/api/show"
time=2025-03-10T14:05:39.957+07:00 level=INFO source=images.go:669 msg="request failed: Get \"https://registry.ollama.ai/v2/library/qwq/manifests/32b\": dial tcp 104.21.75.227:443: connect: bad file descriptor"
[GIN] 2025/03/10 - 14:05:39 | 200 |  133.137209ms |       127.0.0.1 | POST     "/api/pull"
[GIN] 2025/03/10 - 14:05:41 | 200 |      44.125µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/03/10 - 14:05:41 | 404 |    7.534792ms |       127.0.0.1 | POST     "/api/show"
time=2025-03-10T14:05:41.734+07:00 level=INFO source=images.go:669 msg="request failed: Get \"https://registry.ollama.ai/v2/library/qwq/manifests/32b\": dial tcp 104.21.75.227:443: connect: bad file descriptor"
[GIN] 2025/03/10 - 14:05:41 | 200 |    10.53075ms |       127.0.0.1 | POST     "/api/pull"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.5.13

Originally created by @georgemac-labs on GitHub (Mar 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9621 ### What is the issue? Since today, ollama run does not work for models that I haven't already downloaded Examples: ``` $ ollama run qwq:32b pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/qwq/manifests/32b": dial tcp 104.21.75.227:443: connect: bad file descriptor ``` ``` $ollama run phi4-mini pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/phi4-mini/manifests/latest": dial tcp 104.21.75.227:443: connect: bad file descriptor ``` However, curl is able to fetch these URLs just fine ``` $ curl https://registry.ollama.ai/v2/library/qwq/manifests/32b {"schemaVersion":2,"mediaType":"application/vnd.docker.distribution.manifest.v2+json","config":{"mediaType":"application/vnd.docker.container.image.v1+json","digest":"sha256:6a8faa2fb8b028e782399922ea8eef06b55ec45e2dea1e46642b4326af2020f8","size":488},"layers":[{"mediaType":"application/vnd.ollama.image.model","digest":"sha256:c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb","size":19851336256},{"mediaType":"application/vnd.ollama.image.template","digest":"sha256:41190096a061d4e37207f28e5306f56f55b451127a23df8e38b82dca8947cb98","size":1231},{"mediaType":"application/vnd.ollama.image.license","digest":"sha256:d18a5cc71b84bc4af394a31116bd3932b42241de70c77d2b76d69a314ec8aa12","size":11338},{"mediaType":"application/vnd.ollama.image.params","digest":"sha256:4afe5edfdb51c6d15bdb8124bd38ea5642bb6732ae3fd09abe0fefa1ace25caa","size":77}]}% ``` What I'm seeing is the same behaviour described in https://github.com/ollama/ollama/issues/7495 – if I close the menu bar app and run `ollama serve`, the error does not appear. However, in this case, it wants to redownload the model from scratch (I already had 90%). Models that are already downloaded work as normal. This is on MacOS 13.7.2 and I have 100s of GB of storage free. ### Relevant log output ```shell [GIN] 2025/03/10 - 14:05:07 | 200 | 60.291µs | 127.0.0.1 | GET "/api/version" 2025/03/10 14:05:39 routes.go:1215: INFO server config env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/john/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]" time=2025-03-10T14:05:39.601+07:00 level=INFO source=images.go:432 msg="total blobs: 84" time=2025-03-10T14:05:39.602+07:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-03-10T14:05:39.603+07:00 level=INFO source=routes.go:1277 msg="Listening on 127.0.0.1:11434 (version 0.5.13)" time=2025-03-10T14:05:39.671+07:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=metal variant="" compute="" driver=0.0 name="" total="32.0 GiB" available="32.0 GiB" update check failed - TypeError: fetch failed [GIN] 2025/03/10 - 14:05:39 | 200 | 29.584µs | 127.0.0.1 | HEAD "/" [GIN] 2025/03/10 - 14:05:39 | 404 | 1.881209ms | 127.0.0.1 | POST "/api/show" time=2025-03-10T14:05:39.957+07:00 level=INFO source=images.go:669 msg="request failed: Get \"https://registry.ollama.ai/v2/library/qwq/manifests/32b\": dial tcp 104.21.75.227:443: connect: bad file descriptor" [GIN] 2025/03/10 - 14:05:39 | 200 | 133.137209ms | 127.0.0.1 | POST "/api/pull" [GIN] 2025/03/10 - 14:05:41 | 200 | 44.125µs | 127.0.0.1 | HEAD "/" [GIN] 2025/03/10 - 14:05:41 | 404 | 7.534792ms | 127.0.0.1 | POST "/api/show" time=2025-03-10T14:05:41.734+07:00 level=INFO source=images.go:669 msg="request failed: Get \"https://registry.ollama.ai/v2/library/qwq/manifests/32b\": dial tcp 104.21.75.227:443: connect: bad file descriptor" [GIN] 2025/03/10 - 14:05:41 | 200 | 10.53075ms | 127.0.0.1 | POST "/api/pull" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.5.13
GiteaMirror added the bug label 2026-04-12 17:42:06 -05:00
GiteaMirror commented 2026-04-12 17:42:06 -05:00
Author
Owner
Copy Link

@georgemac-labs commented on GitHub (Mar 10, 2025):

Apologies – cause was a local application-level firewall blocking the connection. That must be why the GUI app was blocked, but terminal was not.

<!-- gh-comment-id:2709839284 --> @georgemac-labs commented on GitHub (Mar 10, 2025): Apologies – cause was a local application-level firewall blocking the connection. That must be why the GUI app was blocked, but terminal was not.
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#6278
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?