Skip to content

Accept All すべて承認

LM Studio Blog

25 stories

LM Studio BlogToolsSplash Engine - the fastest local Qwen3.8 on Apple Silicon How to use Splash by Inco AI in LM Studio Bionic

LM Studio BlogToolsSession References and Introspection How Bionic can search persisted session transcripts to recover details across compactions and sessions.

LM Studio BlogToolsHow Auto Review works in Bionic AST parsing, capability extraction, and command matching for safe shell command execution in Bionic's Auto Review mode.

LM Studio BlogToolsBionic now supports skills Teach Bionic repeatable actions with Skills.

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

LM Studio BlogToolsCreate slides and documents using Kimi K3 in Bionic See how Kimi K3 in LM Studio Bionic turns research into polished Word documents and PowerPoint decks.

LM Studio BlogToolsRun DeepSeek V4 Flash locally or in the cloud (US-hosted) DeepSeek V4 Flash is now available locally and in LM Studio Bionic, hosted on US-based servers with Zero Data Retention by default.

LM Studio BlogToolsRun Kimi K3 in LM Studio Bionic MoonshotAI's Kimi K3 is now available in LM Studio Bionic.

LM Studio BlogToolsIntroducing LM Studio Bionic: the AI agent for open models The AI agent made for open models, built to get things done.

LM Studio BlogToolsImproving LM Studio's MLX Engine for Agentic Workflows mlx-engine v1.8.5 dramatically improves performance for repeated, long-context agentic workflows by checkpointing your KV cache.

LM Studio BlogToolsRun (your largest) local models from your iPhone LM Link is now available on iPhone and iPad through Locally, LM Studio's mobile app

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

LM Studio BlogToolsRun open models on NVIDIA DGX Station GB300 LM Studio now supports NVIDIA DGX Station - GB300 Blackwell in a form factor you can run outside of the data center

LM Studio BlogToolsUse your LM Studio Models in Claude Code Run Claude Code with any local model using LM Studio's Anthropic-compatible API

LM Studio BlogToolsIntroducing LM Studio 0.4.0 Server deployment, parallel requests with continuous batching, new REST API endpoint, and refreshed application UI

LM Studio BlogToolsOpen Responses with local models via LM Studio Update to LM Studio 0.3.39 for Open Responses support

LM Studio BlogToolsLM Studio 0.3.37 LFM2 tool call support and a generator stability fix

LM Studio BlogToolsLM Studio 0.3.38 Mac M5 MLX fix, enable optimized MLX auto-upgrade

LM Studio BlogToolsHow to fine-tune FunctionGemma and run it locally Step by step guide for fine-tuning FunctionGemma with Unsloth, and then running it in LM Studio

LM Studio BlogToolsLM Studio 0.3.36 Support for Google's FunctionGemma (270M)

LM Studio BlogToolsLM Studio 0.3.35 Devstral-2, GLM-4.6V, and system prompt fixes

LM Studio BlogToolsLM Studio 0.3.34 EssentialAI rnj-1 support and a Jinja prompt formatting fix

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

LM Studio BlogToolsLM 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.

On the calendar

予定 · Conferences and launch events, this week's stories from each corner of the industry, and what its press is covering — in English

On view

This week, from that corner the newest stories from the corner of the industry you picked

The wire their own posts, translated

How code moves in 2026 from the industry's own reports

Sources

Fetched every six hours, linked to the original

About

The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo