Changelog 👾

Build 5

• Fix Windows on ARM CUDA not detected
• Fixed lms compatibility with Bionic.

Build 4

• Support for /v1/systemone Jev (TypeSafe AI) compatible endpoint
• Support for /v1/decisions OpenAI compatible endpoint

Build 3

• Coexistence with Bionic — Run both apps together; Bionic uses LM Studio for local model inference while LM Studio is running. Requires Bionic 1.1.8 and newer.
• Added CUDA 13 support on Windows ARM.
• UI polish

Build 2

• Updated the llama.cpp runtime to 2.50.0 (upstream b11337).

Build 1

• Bug fixes and security hardening.

Build 1

• [Mac] Added support for the Splash engine on Apple Silicon M3 or newer running macOS 26.4 or newer.

Build 1

• [LM Studio Engine Protocol] Added advanced llama.cpp argument overrides for GGUF model loading
• Improve DSpark and DFlash assistant drafters compatibility heuristics
• Fixed the Loaded Instances UI showing an incorrect context length
• Fixed /api/v1/chat splitting text and image inputs into separate user messages
• Improved sign-in reliability

Build 1

• Improve reliability of Qwen 3.8 Flash Next

Build 1

• Support for DFlash, DSpark, and MTP assistant drafters
  • Requires llama.cpp engine version 2.29.1 or newer
• Added support for images returned by tools in OpenAI-compatible /v1/responses and /v1/chat/completions, and Anthropic-compatible /v1/messages
• [Linux] Fixed AppImage startup on systems without FUSE 2
• [Linux] Fixed AppImage startup when Chromium sandboxing is unavailable
• [Linux] Fixed lms wake-up for AppImage installations
• [Linux] Fixed desktop icons for .deb installations
• [Linux] Enabled in-app updates for AppImage and .deb installations
• [Linux] Improved recovery after canceling .deb update authorization
• [Linux] Fixed keyboard shortcuts becoming unavailable after window focus changes on Wayland

Build 2

• Improved llama.cpp model-load error messages
• Update advanced load settings for mmap, mlock, and direct io for llama.cpp engines 2.28.1 and newer.

Build 1

• Support for local server API key in enterprise internal network endpoint mode

Build 1

• Support for enterprise internal network model endpoint
• Added support for using this device’s models in Bionic over LM Link
• [LM Studio Engine Protocol] Added a developer setting to control the Llama.cpp engine log level

Build 2

• Add /reasoning to lms chat
• [STABLE] Default LM Studio Engine Protocol to ON.

Build 1

• [LM Studio Engine Protocol] Fixed a bug where reasoning would be replayed as non-reasoning content while using /v1/responses or chat UI
• [BETA] Default LM Studio Engine Protocol to ON.

Build 1

• Fixed bug where zooming in and out could cause the interface to scale from the top-left and get clipped
• Fixed a bug where reasoning on/off could be ignored by some models with custom reasoning settings
• Fixed automatic chat title generation for some reasoning models
• Added guidance in model settings for llama.cpp options that move when LM Studio Engine Protocol is enabled

Build 4

• [LM Studio Engine Protocol] Fixed a bug where assistant output was replayed during a continuation request
• [LM Studio Engine Protocol] Off by default, including for users upgrading from beta builds. You can re-enable it in Settings > Developer.
• Add ability to open mermaid diagrams in full screen and save to PNG
• Fix bug in /v1/responses with previous_response_id causing excessive prompt processing

Build 3

• [LM Studio Engine Protocol] Existing custom Chat Template settings in My Models are now preserved when upgrading
• [LM Studio Engine Protocol] Fixed a bug where unsupported GGUF prediction settings could appear in Chat, My Models, and Server configuration panels
  • Chat Template is now in Load Parameters > Advanced, moved from Prediction Parameters > Prompt Template
  • CPU Thread Pool Size is now in Load Parameters > Advanced, moved from Prediction Parameters > Settings > CPU Threads
  • Speculative Decoding settings are now in Load Parameters > Advanced > Speculative Decoding, moved from Prediction Parameters > Speculative Decoding
• [LM Studio Engine Protocol] Fixed automatic chat title generation for some reasoning models
• [LM Studio Engine Protocol] Fixed a bug where RAG document retrieval could fail with some llama.cpp models
• Fix bug where survey failures due to old ROCm versions led to a stuck state of no-GPUs.

Build 2

• iGPUs while using Vulkan backend are now visible and disabled by default
• AMD Strix Halo machines are now supported via the llama.cpp 2.22.1 runtime
• AMD Radeon AI PRO R9600D and R9700 are now supported via the llama.cpp 2.22.1 runtime
• Fixed bug where AMD GPUs were not detected due to driver updates.

Build 1

• [LM Studio Engine Protocol] Added support for prompt template overrides when loading GGUF models
• [LM Studio Engine Protocol] Added support for load-time speculative decoding with vision model support
• [LM Studio Engine Protocol] Enabled by default for supported llama.cpp models
• [LM Studio Engine Protocol] Fix the bug where model would load on the iGPU while using Vulkan on Windows
• Chat to PDF export updated to include styled markdown
• Added support for Mermaid diagram rendering in chat markdown