LM Studio 0.3.5

0.3.5 - Release Notes

Build 10

• New installer

Build 9

• OpenAI-like tool calls now supports streaming! (!)
• Improved tool call reliability through sampling configuration for both streaming and non-streaming tool use
• Fixed lms load command
• Fixed lms unload and lms status not working with embeddings
• Fixed request logging when verbose logging is on (server)
• Fixed some requests/responses are not redacted when logging prompts and responses are off
• Fixed download resuming
• Fixed more accessibility labels on UI elements
• Fixed drag and drop file attachment not working
• [MLX] Fixed bug which degraded performance for certain models

Build 8

• RAG now works again
• Fixed app not launching on some Linux distributions
• Accessibility button label fixes (previously showing Object object)
• Update llama.cpp to commit 46c69e0e (Support for OLMo 2)
• MLX updates
  • Improved performance for MacOS 15
  • Improved performance for VLMs
  • Improved performance for long context generation
  • Bump mlx-engine versions: mlx==0.21.0, mlx_lm==0.20.1, mlx_vlm==0.1.1
  • Support for 3-bit and 6-bit quantization for MLX models

Build 7

• Fixed a bug where models without chat templates, including embedding models, could not be indexed
• Tool use docs are now up on: https://lmstudio.ai/docs/advanced/tool-use
• Improved error reporting in the server API
• Smoother model loader bar resizing on server page

Build 6

• Passing an empty or null tools array in the API request is treated as no tools provided
• Passing an empty or null tool_calls array in assistant messages in the API request is treated as the model making no cool calls

Build 5

• Use any LLM that supports Tool Use and Function Calling through the OpenAI-like API
• Qwen, Mistral, and Llama 3.1/3.2 models work well for tool use
• New in-app "Quick Docs" with code snippets and tool use examples (top right corner)
• Opens in a new window for side-by-side usage in LM Studio
• New role tool in ChatHistoryData that represents the result of a tool call

Build 4

• Fix for file attachments causing an error
• Fix for long chat names pushing chat action buttons in the sidebar
• Update llama.cpp engine: commit SHA ff252ea4

Build 3

• Candidate fix for huggingface model search, download never reachable from within the app ("fetch failed")
• Fix for pasting text from Microsoft Word giving an error about pasting an image
• Fix for structured output for GGUF models lmstudio-bug-tracker/issues/173
• Fix for machines with 1-2 CPU cores getting an error about CPU threads too low

Build 2

• Fixes to in-app update when service mode is enabled
• Fixes to JIT loading across client application lifetime

Build 1

• Run LM Studio as a service (headless)
  • lms load, lms server start no longer requires launching the GUI
  • ability to run on machine startup
• Server start / stop button will remember last setting
  • This is useful when LM Studio is running as a service
• Improvement to Model Search
  • Hugging Face search now happens automatically without Cmd / Ctrl + Enter
• Just-In-Time model loading for OpenAI endpoints
• Button to toggle Mission Control full screen / modal modes
• Update llama.cpp-based JSON response generation; now supports more complex JSON schemas
• Tray menu options to minimize app to tray, copy server base URL
• Checkbox to add lms to PATH during onboarding on Linux
• [Mac][MLX Vision] Bump mlx-vlm version to 0.0.15, support Qwen2VL
• [Mac][MLX Engine] Updated Transformers to 4.45.0
  • Fixes some issues with sideloading quantized MLX models (https://github.com/lmstudio-ai/mlx-engine/issues/10)
• [UI] Move Chat Appearance control to top bar
• [UI] Tweaks to size of per-message action buttons
• Localization:
  • Improved German translation thanks to Goekdeniz-Guelmez
  • Indonesian translation thanks to dwirx
• [Bug fix] fix RAG reinjecting document into context on follow up prompts
• Fixed RAG not working (https://github.com/lmstudio-ai/mlx-engine/issues/4)
• Fix outline flicker around Mission Control