LM Studio Developers

LM Studio with Multi Token Prediction (MTP) is now in beta. 1. Update to 0.4.14+3 in-app 2. Make sure your llama.cpp engine is 2.15.0 3. Turn on MTP when loading a model Use a model that supports it, like Qwen3.6-35B-A3B-MTP-GGUF or Qwen3.6-27B-MTP-GGUF

MTP is available in LM Studio 0.4.14. Sound on.

@ForProduction lmstudio.ai/beta-releases

@lmstudiodevs Download page still says 0.4.13

LM Studio with Multi Token Prediction (MTP) is now in beta. 1. Update to 0.4.14+3 in-app 2. Make sure your llama.cpp engine is 2.15.0 3. Turn on MTP when loading a model Use a model that supports it, like Qwen3.6-35B-A3B-MTP-GGUF or Qwen3.6-27B-MTP-GGUF

@CryZe107 lms runtime update llama.cpp --channel beta

@lmstudiodevs How do I update the llama.cpp engine?

@VinfoCats This might help lmstudio.ai/docs/app/advan…

@lmstudiodevs We need better filters or dedicated UI rather than a popup modal for llm loading. It's hard to navigate when having multiple versions of the same model. Anyways, looking great 👍 congrats on the feature addition! Tested model: qwen3.6-35b-a3b-mtp@bf16 on M5 Max

@uglesado 🤭

@lmstudiodevs God dammit. The only time i ever talked bad about you guys, you proved me wrong in record time

Batching for vision models is now available in Beta with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mode, choose the beta runtime channel, and select LM Studio MLX v1.8.1.

Locally AI is joining LM Studio! We are beyond excited to welcome @adrgrondin and @LocallyAIApp to the LM family. Together we are doubling down on native AI experiences across your devices, anywhere you go. Read our announcement lmstudio.ai/blog/locally-a…

Our servers are overloaded at the moment, and we are working to fix this! Very sorry for the inconvenience. Model search, download, LM Link, and website are impacted. Stay tuned for updates.

We worked with @NVIDIAAI to bring up support for DGX Station GB300 at launch! ✨ 748GB of coherent memory 👾 Install llmster and enable LM Link 🛰️ Load models and use them from other devices Learn how to set it up: lmstudio.ai/blog/dgx-stati… 🚀⚡️🔥

LM Studio 0.4.7 Beta (build 3) is now available. This build contains many bug fixes: 🐛🔨 LaTeX ($ signs) rendering, extraneous <think> tags in coding agents, fixes for tool calling parsing, and more! Update in-app or from lmstudio.ai/beta-releases

【西川和久の不定期コラム】外出先の非力なノートPCで自宅の大型LLMを動かす「LM Link」登場 pc.watch.impress.co.jp/docs/column/ni…

Nemotron 3 Super by @nvidia is now live in LM Studio! 🦾 Open-weight 120B MoE, 12B active params 📜 Supports up to 1M tokens context window Requires about ~83GB to run locally 🚀 lmstudio.ai/models/nemotro…

@FoolaFroos 🔥

Love you even more @lmstudiodevs , you allowed my devices to work in harmony <3 thanks to your LM Link qwen3.5-27b-claude-4.6-opus-reasoning-distilled running on my mac mini 👌😭

One of the coolest uses of @lmstudio and @AIatAMD is using LM Link to have a Framework Desktop be a remote inference server for a laptop, including something little like Framework Laptop 12. It feels native on the laptop, but gets the desktop’s performance.

@dingchilling You should see this in the chat input box. Clicking on it would turn thinking off

@lmstudiodevs how to turn off thinking on this?

|￣￣￣￣￣￣￣￣￣￣￣￣￣ | | lms get qwen3.5-9b | |＿＿＿＿＿＿＿＿＿＿＿＿＿ | (\__/) || (•ㅅ•) || / づ

Introducing LM Link ✨ Connect to remote instances of LM Studio, securely. 🔐 End-to-end encrypted 📡 Load models locally, use them on the go 🖥️ Use local devices, LLM rigs, or cloud VMs Launching in partnership with @Tailscale Try it now: link.lmstudio.ai

Introducing Parallel Requests for MLX! Multiple requests to the same model can now be processed simultaneously ✨🚄⚡️ Works both in the API and in Split View chats. See it in action 👇🕺