LM Studio

LM Studio 0.3.26 Release — Enhanced Log Streaming and Bug Fixes

Stream server, model logs (input and output) with `lms log stream`, native context menus, and bug fixes.

15 Sept 2025

LM Studio 0.3.25 Release: Bulk Actions, Trash Bin, & New Models

Select multiple chats for bulk actions, trash bin support, Google EmbeddingGemma, and NVIDIA Nemotron-Nano-v2 with tool calling capabilities.

4 Sept 2025

LM Studio 0.3.24 Release — ByteDance/Seed-OSS Support & Enhancements

Support for ByteDance/Seed-OSS, improved markdown code blocks and tables, bug fixes.

28 Aug 2025

LM Studio 0.3.23 Release: Improved Tool Calling & MoE Support

Improve in-app chat tool calling reliability for gpt-oss, and ability to place MoE expert weights on CPU

12 Aug 2025

OpenAI's gpt-oss now runs locally in LM Studio

We worked with OpenAI to ensure LM Studio supports running gpt-oss models locally on launch day 🎉

5 Aug 2025

LM Studio 0.3.20 Release — Qwen3-Coder-480B-A35B support added

Bug fixes, UI improvements, and support for Qwen3-Coder-480B-A35B with tools.

23 Jul 2025

LM Studio 0.3.19 Release — AMD GPU and Linux Support

ROCm / Linux support for AMD 9000 series GPUs, bug fixes for model loading, UI improvements, and auto-deletion of engine dependencies to save disk space.

21 Jul 2025

LM Studio 0.3.18 Release — MCP improvements and OpenAI streaming

MCP bug fixes and improvements, OpenAI compat API new streaming options and bug fixes, improved tools calling for Mistral models, and UI touchups.

10 Jul 2025

LM Studio now free for use at work — removes commercial license requirement

Starting today, it's no longer necessary to get a commercial license for using LM Studio at work. No need to fill out a form or contact us. You and your team can just use the app!

8 Jul 2025

LM Studio 0.3.17: Model Context Protocol (MCP) Host support added

New in LM Studio 0.3.17: Model Context Protocol (MCP) Host support. Connect MCP servers to the app and use them with local models.

25 Jun 2025

LM Studio introduces unified multi-modal MLX engine architecture

Leveraging `mlx-lm` and `mlx-vlm` to achieve unified multi-modal LLM inference in LM Studio's `mlx-engine`.

30 May 2025

DeepSeek R1-0528 Model Released - Run Locally with 4GB RAM

Run the distilled DeepSeek R1 0528 model (8B) locally in LM Studio on Mac, Windows, or Linux with as little as 4GB of RAM. Supports tool use and reasoning.

29 May 2025

LM Studio 0.3.16 Release: Community Presets, Embedding Models, and REST API

Public Preview of community presets, automatic deletion of least recently used Runtime Extension Packs, and a way to use LLMs as text embedding models.

23 May 2025

LM Studio 0.3.15: RTX 50-series GPUs and improved tool use in the API

Support for CUDA 12, new system prompt editor UI, improved tool use API support, and preview of community presets.

24 Apr 2025

LM Studio 0.3.14: Multi-GPU Controls Released

Advanced controls for multi-GPU setups: enable/disable specific GPUs, choose allocation strategy, limit model weight to dedicated GPU memory, and more.

27 Mar 2025

LM Studio 0.3.13: Google Gemma 3 Support Added

LM Studio 0.3.13 supports Google's latest multi-modal model, Gemma 3. Run it locally on your Mac, Windows, or Linux machine.

12 Mar 2025

LM Studio 0.3.12 Release — RAG performance and bug fixes

Bug fixes and document chunking speed improvements for RAG

7 Mar 2025

OpenVoice releases lmstudio-python and lmstudio-js SDKs

Developer SDKs for Python and TypeScript are now available in a 1.0.0 release. A programmable toolkit for local AI software.

3 Mar 2025

LM Studio 0.3.11 Release: SDK, Speculative Decoding, Bug Fixes

Support for LM Studio SDK (Python, TS/JS), advanced Speculative Decoding settings, and bug fixes

3 Mar 2025

LM Studio 0.3.10: Speculative Decoding for Faster Inference

Inference speed up with Speculative Decoding for `llama.cpp` and `MLX`

18 Feb 2025