Changelog 👾

Build 2

• Lm Link no longer requires waitlisting
• Updated default context length to 8k tokens

Build 1

• Introducing Locally, LM Studio's mobile app. Available on iPhone and iPad.
  • Use LM Link in Locally to take your largest LM Studio models on the go
• Security hardening
• [GGUF] Fix multi-GPU selection bugs affecting GPU ON/OFF and Priority Order on some CUDA 12, ROCm, and Vulkan setups

Build 1

• Introducing Locally, LM Studio's mobile app. Available on iPhone and iPad.
  • Use LM Link in Locally to take your largest LM Studio models on the go
• Security hardening
• [GGUF] Fix multi-GPU selection bugs affecting GPU ON/OFF and Priority Order on some CUDA 12, ROCm, and Vulkan setups

Build 2

• [CUDA] Added tensor parallelism support for multi-GPU model loading
• [llama.cpp] Added a Physical Batch Size advanced load option
• Fixed REST API requests hanging when HTTP/2 clients sent upgrade headers
• Fixed image attachments appearing in reverse order after sending a chat message
• Fixed a bug where double clicking model trigger would re-open it
• Fixed tool type error bug while using codex --oss
• Fixed invalid role error while using Claude Code. /v1/messages API now supports system messages in the messages array

Build 1

• LM Studio Engine Protocol beta 2
  • New architecture to enable us to ship more frequent engine updates
  • Turn it on in Settings > Developer > Enable LM Studio Engine Protocol
• Fixed a bug which dropped prompt cache on every message when using Claude Code, improving performance significantly
• Fixed a bug when using theme picker overlay over other modals
• Fixed a z-index bug in the Models Table scroll
• Security hardening

Build 4

• Stable release of MTP Speculative Decoding!
  • Speeds up generation with models that include built-in multi-token prediction heads
  • To try it out, download an MTP-capable model
• Fixed an issue with non-MTP speculative decoding error while MTP was enabled
• Fixed a bug where lms get gemma4 would not show any results
• lms chat now shows which LM Link device each remote model is on

Build 3

• Fixed a chat UI bug that could remove whitespace when using MTP

Build 2

• Beta release of MTP Speculative Decoding
• Fixed token exchange failure for few MCPs in OAuth flow

Build 1

• Beta build of LM Studio Engine Protocol

Build 1

• [MLX] mlx-engine v1.8.1 significantly improves performance and adds parallel predictions for vision-capable models such as Qwen 3.5/3.6 and Gemma 4
• Fixed a bug where newlines were compacted in the chat input on paste
• Bug fixes and security hardening. This update is recommended for all users.

Build 1

• Support for Qwen 3.6
• Improved style in chat PDF exports
• Fixed bug where MCP servers with OAuth would not work on some Windows environments
• Improved Qwen 3.5 performance with OpenAI-compatible /v1/chat/completions, /v1/responses and Anthropic-compatible /v1/messages

Build 1

• Support for updated Gemma 4 chat template

Build 1

• Improve Gemma 4 tool call reliability
• Add OAuth support for MCP servers

Build 1

• Improve Gemma 4 tool call reliability
• Add support for Anthropic-compatible v1/messages output_config.effort (low, medium, high, max)
• Fixed a bug where deleting a chat folder would sometimes freeze the UI
• Fixed a bug where markdown Link popovers would appear at the top of the window

Build 1

• Add support for reasoning_effort and reasoning_tokens in OpenAI-compatible v1/chat/completions
• Adds a reasoning field to the /api/v1/models API response, indicating each model's supported reasoning capabilities/REST configuration options learn more
• Fixed a bug where Insert in chat input would sometimes not work after toggling assistant and user mode
• Fixed a bug where surrounding spaces in tool call parameters would be stripped for models that uses XML/XML-like tool call formats
• [CUDA] Fixed issue where some VRAM would not be deallocated under certain conditions
• Fixes a bug where setting reasoning to low when using Nemotron 3 Super via the /api/v1/chat or OpenAI-compatible /v1/responses API would error out