lmstudio-ai / lmstudio-ai/lmstudio-python
Loading a model through the SDK does not use per model defaults
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 875
- Forks
- 166
- PR merge metrics
- No merged PRs in 30d
Description
Let’s take Qwen3 1.7B. The installed model default temp is 0.8.
I change the default temp to 0.6.
When I load the model in the UI, the temp is 0.8.
If I use the cli with lms load, the temp is 0.8.
If I use the REST API v1, the temp is 0.8
If I use the python sdk lmstudio.llm(), the temp is not 0.8, but back to 0.6.
The other params follow the same pattern - use my custom defaults when loaded everywhere except the python sdk.
The SDK should load using the per model custom defaults I set.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the Python SDK entry point lmstudio.llm() and trace how model-loading parameters are selected. Compare its handling of per-model custom defaults with the UI, CLI lms load, and REST API v1 behavior described in the issue. Done means SDK-loaded models use the configured per-model defaults, including temperature and the other parameters.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100