Blog

Past posts

Run Muse Glimmer locally

Run Muse Glimmer locally

Meta's new 30B agentic open-source model is available LM Studio Bionic.

Aug 10, 2026
Locally AI joins LM Studio

Locally AI joins LM Studio

Adrien and the Locally AI apps are joining the LM Studio family to double down on Apple platforms

Apr 8, 2026
Introducing LM Studio 0.4.0

Introducing LM Studio 0.4.0

Server deployment, parallel requests with continuous batching, new REST API endpoint, and refreshed application UI

Jan 28, 2026
LM Studio 0.3.37

LM Studio 0.3.37

LFM2 tool call support and a generator stability fix

Jan 6, 2026
LM Studio 0.3.38

LM Studio 0.3.38

Mac M5 MLX fix, enable optimized MLX auto-upgrade

Jan 6, 2026
LM Studio 0.3.36

LM Studio 0.3.36

Support for Google's FunctionGemma (270M)

Dec 18, 2025
LM Studio 0.3.35

LM Studio 0.3.35

Devstral-2, GLM-4.6V, and system prompt fixes

Dec 12, 2025
LM Studio 0.3.34

LM Studio 0.3.34

EssentialAI rnj-1 support and a Jinja prompt formatting fix

Dec 10, 2025
Ministral 3

Ministral 3

LM Studio 0.3.33: Ministral 3 support, Olmo-3 tool calling, and release notes

Dec 2, 2025
LM Studio 0.3.32

LM Studio 0.3.32

GLM 4.5 tool calling, olmOCR-2, improved image input handling in `/v1/responses`, Flash Attention defaults for Vulkan/Metal, and bug fixes.

Nov 19, 2025
LM Studio 0.3.31

LM Studio 0.3.31

Image input improvements, MiniMax M2 tool calling, Flash Attention default for CUDA, new CLI runtime management, macOS 26 support, and bug fixes.

Nov 4, 2025
OpenAI gpt-oss-safeguard

OpenAI gpt-oss-safeguard

Open safety reasoning models (120B and 20B) with bring-your-own-policy moderation, now supported in LM Studio on launch day.

Oct 29, 2025
NVIDIA DGX Spark

NVIDIA DGX Spark

LM Studio now ships for Linux on ARM and launches with NVIDIA DGX Spark — a tiny but mighty Linux ARM box.

Oct 14, 2025
LM Studio 0.3.30

LM Studio 0.3.30

Bug fixes: Qwen tool-calling streaming, Vulkan iGPU loading, and `developer` role support in `/v1/responses`.

Oct 8, 2025
LM Studio 0.3.28

LM Studio 0.3.28

Default model‑variant selection in My Models, better RAM/VRAM estimates (mixed quantizations, mislabeled params, non‑transformers), and bug fixes.

Oct 1, 2025
LM Studio 0.3.26

LM Studio 0.3.26

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

Sep 15, 2025
LM Studio 0.3.25

LM Studio 0.3.25

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

Sep 4, 2025
LM Studio 0.3.24

LM Studio 0.3.24

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

Aug 28, 2025
LM Studio 0.3.23

LM Studio 0.3.23

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

Aug 12, 2025
LM Studio 0.3.20

LM Studio 0.3.20

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

Jul 23, 2025
LM Studio 0.3.19

LM Studio 0.3.19

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.

Jul 21, 2025
LM Studio 0.3.18

LM Studio 0.3.18

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

Jul 10, 2025
LM Studio is free for use at work

LM Studio is free for use at work

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!

Jul 8, 2025
MCP in LM Studio

MCP in LM Studio

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.

Jun 25, 2025
DeepSeek-R1-0528 you can run on your computer

DeepSeek-R1-0528 you can run on your computer

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.

May 29, 2025
LM Studio 0.3.16

LM Studio 0.3.16

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

May 23, 2025
LM Studio 0.3.14: Multi-GPU Controls 🎛️

LM Studio 0.3.14: Multi-GPU Controls 🎛️

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

Mar 27, 2025
LM Studio 0.3.13: Google Gemma 3 Support

LM Studio 0.3.13: Google Gemma 3 Support

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

Mar 12, 2025
LM Studio 0.3.12

LM Studio 0.3.12

Bug fixes and document chunking speed improvements for RAG

Mar 7, 2025
LM Studio 0.3.11

LM Studio 0.3.11

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

Mar 3, 2025
LM Studio 0.3.9

LM Studio 0.3.9

Idle TTL, auto-update for runtimes, support for nested folders in HF repos, and separate `reasoning_content` in chat completion responses

Jan 30, 2025
LM Studio 0.3.8

LM Studio 0.3.8

Thinking UI for DeepSeek R1, LaTeX rendering improvements, and bug fixes

Jan 21, 2025
LM Studio 0.3.7

LM Studio 0.3.7

DeepSeek R1 support and KV Cache quantization for llama.cpp models

Jan 20, 2025
LM Studio 0.3.6

LM Studio 0.3.6

Tool Calling API in beta, new installer / updater system, and support for `Qwen2VL` and `QVQ` (both GGUF and MLX)

Jan 6, 2025
LM Studio 0.3.5

LM Studio 0.3.5

Headless mode, on-demand model loading, server auto-start, CLI command to download models from the terminal, and support for Pixtral with Apple MLX.

Oct 22, 2024
LM Studio 0.3.3

LM Studio 0.3.3

Config presets are back! So are live token counts for user input and system prompt. Many bug fixes. Also several new app languages thanks to community contributors.

Sep 30, 2024
LM Studio 0.3.0

LM Studio 0.3.0

LM Studio 0.3.0 is here! Built-in (naïve) RAG, light theme, internationalization, Structured Outputs API, Serve on the network, and more.

Aug 22, 2024
Llama 3.1

Llama 3.1

Run Llama 3.1 locally on your computer with LM Studio.

Jul 23, 2024