github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 05:31:43 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13441] Ollama CLI can't reach remote instances, but curl works #8874

New Issue
Closed
opened 2026-04-12 21:40:48 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 21:40:48 -05:00
Owner
Copy Link

Originally created by @XanderStrike on GitHub (Dec 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13441

What is the issue?

With Ollama running on a remote machine with IP 192.168.0.118 with podman:

podman run -d --replace --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -e OLLAMA_HOST=0.0.0.0 -e OLLAMA_ORIGINS=* -p 11434:11434 --name ollama docker.io/ollama/ollama:rocm

I am unable to reach it using the Ollama CLI:

$ OLLAMA_HOST=http://192.168.0.118:11434 ollama list
Error: Head "http://192.168.0.118:11434/": dial tcp 192.168.0.118:11434: connect: no route to host

There is nothing wrong with my network, I can curl the API no problem:

$ curl -s http://192.168.0.118:11434/api/tags | jq '.models[].name' | grep devstral
"devstral-small-2:latest"
"devstral:24b"
"devstral:latest"

This appears to be a new issue, the same setup was working fine with older versions (not sure which) but I had to update to run devstral-small-2.

Relevant log output

Only the `curl` actually reaches ollama and it shows normal 


time=2025-12-12T18:55:38.842Z level=INFO source=routes.go:1554 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-12-12T18:55:38.846Z level=INFO source=images.go:522 msg="total blobs: 135"
time=2025-12-12T18:55:38.847Z level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-12-12T18:55:38.847Z level=INFO source=routes.go:1607 msg="Listening on [::]:11434 (version 0.13.3)"
time=2025-12-12T18:55:38.847Z level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-12-12T18:55:38.847Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37605"
time=2025-12-12T18:55:39.331Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 35533"
time=2025-12-12T18:55:39.856Z level=INFO source=types.go:42 msg="inference compute" id=GPU-ad3c84398f492136 filter_id="" library=ROCm compute=gfx1201 name=ROCm0 description="AMD Radeon Graphics" libdirs=ollama,rocm driver=60342.13 pci_id=0000:03:00.0 type=discrete total="15.9 GiB" available="14.7 GiB"
time=2025-12-12T18:55:39.856Z level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="15.9 GiB" threshold="20.0 GiB"
[GIN] 2025/12/12 - 18:55:45 | 200 |     6.96964ms |   192.168.0.182 | GET      "/api/tags"
[GIN] 2025/12/12 - 18:55:45 | 200 |    6.054606ms |   192.168.0.182 | GET      "/api/tags"
[GIN] 2025/12/12 - 18:55:52 | 200 |    6.232241ms |   192.168.0.182 | GET      "/api/tags"
[GIN] 2025/12/12 - 18:56:00 | 200 |    7.245405ms |   192.168.0.182 | GET      "/api/tags"

OS

Linux

GPU

AMD

CPU

Intel

Ollama version

both server and client are on 0.13.3

Originally created by @XanderStrike on GitHub (Dec 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13441 ### What is the issue? With Ollama running on a remote machine with IP `192.168.0.118` with podman: ``` podman run -d --replace --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -e OLLAMA_HOST=0.0.0.0 -e OLLAMA_ORIGINS=* -p 11434:11434 --name ollama docker.io/ollama/ollama:rocm ``` I am unable to reach it using the Ollama CLI: ``` $ OLLAMA_HOST=http://192.168.0.118:11434 ollama list Error: Head "http://192.168.0.118:11434/": dial tcp 192.168.0.118:11434: connect: no route to host ``` There is nothing wrong with my network, I can curl the API no problem: ``` $ curl -s http://192.168.0.118:11434/api/tags | jq '.models[].name' | grep devstral "devstral-small-2:latest" "devstral:24b" "devstral:latest" ``` This appears to be a new issue, the same setup was working fine with older versions (not sure which) but I had to update to run `devstral-small-2`. ### Relevant log output ```shell Only the `curl` actually reaches ollama and it shows normal time=2025-12-12T18:55:38.842Z level=INFO source=routes.go:1554 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-12-12T18:55:38.846Z level=INFO source=images.go:522 msg="total blobs: 135" time=2025-12-12T18:55:38.847Z level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-12-12T18:55:38.847Z level=INFO source=routes.go:1607 msg="Listening on [::]:11434 (version 0.13.3)" time=2025-12-12T18:55:38.847Z level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-12-12T18:55:38.847Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 37605" time=2025-12-12T18:55:39.331Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 35533" time=2025-12-12T18:55:39.856Z level=INFO source=types.go:42 msg="inference compute" id=GPU-ad3c84398f492136 filter_id="" library=ROCm compute=gfx1201 name=ROCm0 description="AMD Radeon Graphics" libdirs=ollama,rocm driver=60342.13 pci_id=0000:03:00.0 type=discrete total="15.9 GiB" available="14.7 GiB" time=2025-12-12T18:55:39.856Z level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="15.9 GiB" threshold="20.0 GiB" [GIN] 2025/12/12 - 18:55:45 | 200 | 6.96964ms | 192.168.0.182 | GET "/api/tags" [GIN] 2025/12/12 - 18:55:45 | 200 | 6.054606ms | 192.168.0.182 | GET "/api/tags" [GIN] 2025/12/12 - 18:55:52 | 200 | 6.232241ms | 192.168.0.182 | GET "/api/tags" [GIN] 2025/12/12 - 18:56:00 | 200 | 7.245405ms | 192.168.0.182 | GET "/api/tags" ``` ### OS Linux ### GPU AMD ### CPU Intel ### Ollama version both server and client are on 0.13.3
GiteaMirror added the bug label 2026-04-12 21:40:48 -05:00
GiteaMirror commented 2026-04-12 21:40:51 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 13, 2025):

Unable to repro. I started ollama:0.13.3-rocm in docker on an evo-x2 and was able to connect from a different machine on the LAN:

$ OLLAMA_HOST=http://192.168.0.118:11434 ollama -v
ollama version is 0.13.3
$ OLLAMA_HOST=http://192.168.0.118:11434 ollama list
NAME                                                                                              ID              SIZE       MODIFIED      
devstral:latest                                                                                   9bd74193e939    14 GB      5 minutes ago    
devstral:24b                                                                                      9bd74193e939    14 GB      5 minutes ago    
devstral-small-2:latest                                                                           24277f07f62d    15 GB      5 minutes ago    
...
$ curl -s http://192.168.0.118:11434/api/tags | jq '.models[].name' | grep devstral
"devstral:latest"
"devstral:24b"
"devstral-small-2:latest"
<!-- gh-comment-id:3648754603 --> @rick-github commented on GitHub (Dec 13, 2025): Unable to repro. I started ollama:0.13.3-rocm in docker on an evo-x2 and was able to connect from a different machine on the LAN: ```console $ OLLAMA_HOST=http://192.168.0.118:11434 ollama -v ollama version is 0.13.3 $ OLLAMA_HOST=http://192.168.0.118:11434 ollama list NAME ID SIZE MODIFIED devstral:latest 9bd74193e939 14 GB 5 minutes ago devstral:24b 9bd74193e939 14 GB 5 minutes ago devstral-small-2:latest 24277f07f62d 15 GB 5 minutes ago ... $ curl -s http://192.168.0.118:11434/api/tags | jq '.models[].name' | grep devstral "devstral:latest" "devstral:24b" "devstral-small-2:latest" ```
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#8874
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?