github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-20 21:13:41 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9083] OLLAMA_HOST Ignored After Upgrading to v0.5.9 on macOS #5910

New Issue
Closed
opened 2026-04-12 17:14:49 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 17:14:49 -05:00
Owner
Copy Link
Copy Source

Originally created by @cloverzrg on GitHub (Feb 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9083

What is the issue?

After upgrading Ollama from v0.5.7 to v0.5.9 on macOS, I noticed that the system no longer respects the OLLAMA_HOST environment variable when startup app. Instead of using the specified address in OLLAMA_HOST, the system defaults to 127.0.0.1. However, when manually executing ollama serve, the correct OLLAMA_HOST value is used.

Environment:

  • Shell: zsh
  • Configuration: export OLLAMA_HOST=x.x.x.x set in .zshrc

Relevant log output

2025/02/14 10:07:27 routes.go:1186: INFO server config env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: 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/xxx/.ollama/models OLLAMA_MULTIUSER_CACHE: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://*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]"
time=2025-02-14T10:07:27.634+08:00 level=INFO source=images.go:432 msg="total blobs: 5"
time=2025-02-14T10:07:27.634+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-02-14T10:07:27.635+08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.9)"
time=2025-02-14T10:07:27.693+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=metal variant="" compute="" driver=0.0 name="" total="10.7 GiB" available="10.7 GiB"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

v0.5.9

Originally created by @cloverzrg on GitHub (Feb 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9083 ### What is the issue? After upgrading Ollama from v0.5.7 to v0.5.9 on macOS, I noticed that the system no longer respects the OLLAMA_HOST environment variable when startup app. Instead of using the specified address in OLLAMA_HOST, the system defaults to 127.0.0.1. However, when manually executing `ollama serve`, the correct OLLAMA_HOST value is used. ## Environment: * Shell: zsh * Configuration: export OLLAMA_HOST=x.x.x.x set in .zshrc ### Relevant log output ```shell 2025/02/14 10:07:27 routes.go:1186: INFO server config env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: 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/xxx/.ollama/models OLLAMA_MULTIUSER_CACHE: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://*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]" time=2025-02-14T10:07:27.634+08:00 level=INFO source=images.go:432 msg="total blobs: 5" time=2025-02-14T10:07:27.634+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-14T10:07:27.635+08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.9)" time=2025-02-14T10:07:27.693+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=metal variant="" compute="" driver=0.0 name="" total="10.7 GiB" available="10.7 GiB" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version v0.5.9
GiteaMirror added the bug label 2026-04-12 17:14:49 -05:00
GiteaMirror commented 2026-04-12 17:14:52 -05:00
Author
Owner
Copy Link
Copy Source

@rick-github commented on GitHub (Feb 14, 2025):

Did you try

launchctl setenv OLLAMA_HOST "x.x.x.x"
<!-- gh-comment-id:2658133965 --> @rick-github commented on GitHub (Feb 14, 2025): Did you try ``` launchctl setenv OLLAMA_HOST "x.x.x.x" ```
GiteaMirror commented 2026-04-12 17:14:52 -05:00
Author
Owner
Copy Link
Copy Source

@cloverzrg commented on GitHub (Feb 14, 2025):

Did you try

launchctl setenv OLLAMA_HOST "x.x.x.x"

After exec launchctl setenv OLLAMA_HOST "x.x.x.x", it works, but the env set in .zshrc is work in v0.5.7, if this is not a issue, please close it

<!-- gh-comment-id:2658147691 --> @cloverzrg commented on GitHub (Feb 14, 2025): > Did you try > > ``` > launchctl setenv OLLAMA_HOST "x.x.x.x" > ``` After exec `launchctl setenv OLLAMA_HOST "x.x.x.x"`, it works, but the env set in .zshrc is work in v0.5.7, if this is not a issue, please close it
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 labels bug
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5910