Issue Station
Sign In
Tools hereToolbox

ollama - ✅(Solved) Fix ollama launch openclaw --model You still need to download the model the first time you start it when choosing a model [1 pull requests, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#14990•Fetched 2026-04-08 01:08:16
View on GitHub
Comments
0
Participants
1
Timeline
3
Reactions
0
Author
AkidofiwannaAkidofiwanna
Participants
AkidofiwannaAkidofiwanna
Assignees
ParthSareenParthSareen
Timeline (top)
assigned ×1cross-referenced ×1labeled ×1

Fix Action

Fixed

PR fix notes

PR #14993: launch: fix openclaw --model override handling

Description (problem / solution / changelog)

ollama launch openclaw --model <model> was still running readiness checks against saved secondary models, so an explicit launch like --model kimi-k2.5:cloud could still prompt to download qwen3.5:35b.

Only ensure the override model during launch while preserving saved secondary models in config. Also normalize cached OpenClaw session model state (modelOverride / providerOverride and runtime model / modelProvider) so the new primary model takes effect immediately instead of being shadowed by stale session data.

Fixes #14990.

Changed files

  • cmd/launch/launch.go (modified, +11/-2)
  • cmd/launch/launch_test.go (modified, +59/-0)
  • cmd/launch/openclaw.go (modified, +90/-19)
  • cmd/launch/openclaw_test.go (modified, +152/-7)
RAW_BUFFERClick to expand / collapse

What is the issue?

<img width="1623" height="496" alt="Image" src="https://github.com/user-attachments/assets/9fd08636-4c3d-4a32-af68-cb5398bac68b" /> why need download qwen3.5:35b?

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

extent analysis

Fix Plan

The fix involves updating the dependencies to ensure compatibility and resolving the download issue for the required package.

  • Check the package version and update it if necessary
  • Verify the package repository and update the package list
  • Install the required package (e.g., qwen3.5:35b) using the package manager

Example Code

# Update package list
sudo apt update

# Install the required package
sudo apt install qwen3.5

# If the package is not found, try searching for it
sudo apt search qwen

Verification

To verify that the fix worked, check if the package is installed correctly and if the issue is resolved.

# Check if the package is installed
dpkg -l | grep qwen

Extra Tips

  • Make sure to update the package list regularly to ensure you have the latest packages.
  • If the package is not found in the default repository, you may need to add a third-party repository or install it from source.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#installation#tensor shape#autograd error#prompt template#agent execution#callback error#memory management#API rate limit

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING