github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12966] Model runs forever on Windows even with minimal model smollm:135m #8595

New Issue
Closed
opened 2026-04-12 21:19:36 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 21:19:36 -05:00
Owner
Copy Link

Originally created by @natgate on GitHub (Nov 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12966

Description

Summary:
On Windows 10 (Intel i7-7500U, 16 GB RAM), running the smallest model smollm:135m never produces a response.
Generation hangs indefinitely — no tokens are returned.
This happens both from the Ollama desktop app and the PowerShell API call.

System Information

  • OS: Windows 10 22H2 (64-bit)
  • CPU: Intel Core i7-7500U @ 2.70 GHz (2 cores / 4 threads)
  • RAM: 16 GB
  • GPU: NVIDIA 940MX (unsupported, so CPU-only mode)
  • Ollama version: 0.12.9
  • Model: smollm:135m

Reproduction Steps

  1. Start Ollama (CPU-only mode).
  2. Run the following PowerShell command: 
    (Invoke-WebRequest -Method POST -Body '{"model":"smollm:135m", "prompt":"hi", "stream": false}' -Uri http://localhost:11434/api/generate ).Content | ConvertFrom-Json
  3. Observe that the process never returns any text — it hangs indefinitely.

Expected Behavior

The model should return a short reply such as "Hello!" within a few seconds.

Actual Behavior

The command runs forever; no output is produced.

Relevant Log Snippet

time=2025-11-05T11:29:15.294+01:00 level=DEBUG source=runner.go:471 msg="bootstrap discovery took" duration=117.8962ms OLLAMA_LIBRARY_PATH="[D:\programs\lib\ollama D:\programs\lib\ollama\rocm]" extra_envs=map[]
time=2025-11-05T11:29:15.295+01:00 level=DEBUG source=runner.go:120 msg="evluating which if any devices to filter out" initial_count=0
time=2025-11-05T11:29:15.296+01:00 level=DEBUG source=runner.go:41 msg="GPU bootstrap discovery took" duration=509.5988ms
time=2025-11-05T11:29:15.300+01:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="15.9 GiB" available="9.0 GiB"
time=2025-11-05T11:29:15.300+01:00 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
time=2025-11-05T11:29:27.454+01:00 level=DEBUG source=runner.go:267 msg="refreshing free memory"
time=2025-11-05T11:29:27.454+01:00 level=DEBUG source=runner.go:41 msg="overall device VRAM discovery took" duration=0s

Notes

  • Model files are stored on D:\Ollama\models

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.9

Originally created by @natgate on GitHub (Nov 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12966 ## Description **Summary:** On Windows 10 (Intel i7-7500U, 16 GB RAM), running the smallest model `smollm:135m` never produces a response. Generation hangs indefinitely — no tokens are returned. This happens both from the Ollama desktop app and the PowerShell API call. --- ## System Information - **OS:** Windows 10 22H2 (64-bit) - **CPU:** Intel Core i7-7500U @ 2.70 GHz (2 cores / 4 threads) - **RAM:** 16 GB - **GPU:** NVIDIA 940MX (unsupported, so CPU-only mode) - **Ollama version:** 0.12.9 - **Model:** `smollm:135m` --- ## Reproduction Steps 1. Start Ollama (CPU-only mode). 2. Run the following PowerShell command: ```powershell (Invoke-WebRequest -Method POST -Body '{"model":"smollm:135m", "prompt":"hi", "stream": false}' -Uri http://localhost:11434/api/generate ).Content | ConvertFrom-Json ``` 3. Observe that the process never returns any text — it hangs indefinitely. --- ## Expected Behavior The model should return a short reply such as `"Hello!"` within a few seconds. --- ## Actual Behavior The command runs forever; no output is produced. --- ## Relevant Log Snippet ``` time=2025-11-05T11:29:15.294+01:00 level=DEBUG source=runner.go:471 msg="bootstrap discovery took" duration=117.8962ms OLLAMA_LIBRARY_PATH="[D:\programs\lib\ollama D:\programs\lib\ollama\rocm]" extra_envs=map[] time=2025-11-05T11:29:15.295+01:00 level=DEBUG source=runner.go:120 msg="evluating which if any devices to filter out" initial_count=0 time=2025-11-05T11:29:15.296+01:00 level=DEBUG source=runner.go:41 msg="GPU bootstrap discovery took" duration=509.5988ms time=2025-11-05T11:29:15.300+01:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="15.9 GiB" available="9.0 GiB" time=2025-11-05T11:29:15.300+01:00 level=INFO source=routes.go:1618 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" time=2025-11-05T11:29:27.454+01:00 level=DEBUG source=runner.go:267 msg="refreshing free memory" time=2025-11-05T11:29:27.454+01:00 level=DEBUG source=runner.go:41 msg="overall device VRAM discovery took" duration=0s ``` --- ## Notes - Model files are stored on `D:\Ollama\models` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.9
GiteaMirror added the bug label 2026-04-12 21:19:36 -05:00
GiteaMirror commented 2026-04-12 21:19:38 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 5, 2025):

https://github.com/ollama/ollama/issues/12699

<!-- gh-comment-id:3490516483 --> @rick-github commented on GitHub (Nov 5, 2025): https://github.com/ollama/ollama/issues/12699
GiteaMirror commented 2026-04-12 21:19:39 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Nov 5, 2025):

Going to close this as a dupe, but we can re-open if it's not solved in 0.12.10.

<!-- gh-comment-id:3493800411 --> @pdevine commented on GitHub (Nov 5, 2025): Going to close this as a dupe, but we can re-open if it's not solved in `0.12.10`.
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#8595
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?