LM Studio 0.3.18
LM Studio 0.3.18 is now available as a stable release. This version includes bug fixes and improvements for MCP such as ability to force restart an MCP server and button to refresh MCP server tools. This release also introduces better tool calling for Mistral models, OpenAI API streaming options and bug fixes including include_usage for streaming, and more.
📣 ICYMI: LM Studio is now free for work! Read more https://lmstudio.ai/blog/free-for-work
LM Studio 0.3.18 - Full Release Notes
Upgrade via in-app update, or from https://lmstudio.ai/download.
Build 3
- Fixed the format of errors when streaming from OpenAI compatible endpoints to match the expected format
- Added tool calling support for Mistral v13 tokenizer models (with proper chat templates)
Build 2
- Added support for
"stream_options": { "include_usage": true }when streaming using OpenAI compatible endpoints - Upgrade @huggingface/jinja to version 0.5.0 to support more prompt templates
- Fixed a bug where the app would recommend an excessively large first model for computers that can only do CPU inference
- Fixed a bug where you cannot disable errored plugins
- Adds Hindi and Marathi translations
Build 1
- MCP: option to force restart an MCP server under the ••• menu
- MCP: added a button to refresh the list of tools
- Responsive UI for Mission Control on narrow windows
- Show Chat screen sidebars in popovers when the app window is narrow
- Added a
timeoutfield to entries inmcp.jsonwhich can be used to specify max time for each tool call in milliseconds - Added experimental JavaScript code interpreter plugin using Deno
- Interested in plugins? Sign up for the plugins private beta here: https://forms.gle/ZPfGLMvVC6DbSRQm9
- Various UI and color adjustments
- Fixed a bug where chat message draft and attached files would not carry over to a newly created chat
- Fixed a bug where tool use does not work with llama models (
this.endToolCallStrings is not iterable) - Fixed a bug with OpenAI compatible endpoint where
response_format.typedid not supporttext - Fixed a bug where parallel tool calls that are split across multiple "chunks" were being silently dropped
- Fixed a bug where SSE MCP servers would not work correctly
- Fixed a bug where root level $defs were being stripped in tool definitions
Resources
- Download LM Studio: lmstudio.ai/download
- Report bugs: lmstudio-bug-tracker
- X / Twitter: @lmstudio
- Discord: LM Studio Community