Matthew invested in the company; calls it the easiest product for running local AI, though still not dead simple due to hardware and model differences.
Desktop app for downloading and running local LLMs, now with Bionic, an agent for work and code.
Updated EU status checked Last shown
LM Studio at a glance
- What is LM Studio?
- LM Studio is an app from LM Studio. Desktop app for downloading and running local LLMs, now with Bionic, an agent for work and code.
- Who makes LM Studio?
- LM Studio is made by LM Studio.
- Does LM Studio work in the EU?
- Available in the EU. The privacy policy has a dedicated section for individuals in the EU/UK with GDPR rights, and no EU exclusion was found. Data is transferred to the US, and paid cloud models are US-hosted, so there is no EU data residency. Last verified 14 Nov 2026.
- How much does LM Studio cost?
- Freemium. Free plan for local models and Bionic agent; Bionic+ adds US-hosted open models, discounted bulk tokens and web search; Pro adds 5× usage limits and early access. Exact prices not stated in provided material. Licence: Proprietary.
- Where was LM Studio shown?
- In 2 creator videos by Matthew Berman, Matt Wolfe. Most recently by Matthew Berman on 23 Oct 2026, at 14:36 in “Who is local AI really for?”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
LM Studio is a desktop application for downloading and running open-weights language models locally. It uses the LM Studio runtime with llama.cpp and MLX under the hood, and supports simple chat as well as agentic tasks with locally run models.
Its current focus is Bionic, an agent that creates and edits documents, slides and PDFs, writes code, runs automations and can control the computer. Documents are saved automatically after each change. The app also provides real-time voice transcription that the vendor says is processed locally on the device, with multi-language support.
The Free plan covers running local models, the Bionic agent, offline voice transcription, LM Link for up to 5 devices and limited web search. Paid plans (Bionic+ and Pro) add US-hosted open-source models such as Kimi K3, GLM 5.3 and DeepSeek V4 Flash, plus web search and page extraction; the vendor states its cloud services use Zero Data Retention. Local performance depends on the user's hardware and the chosen model. The software itself is closed-source; specific prices were not given in the provided material.
- Download and run local LLMs via llama.cpp and MLX
- Bionic agent for documents, slides, PDFs, code and computer control
- Offline real-time voice transcription, multiple languages
- LM Link for connecting up to 5 devices on the Free plan
- Optional US-hosted open models on paid plans with Zero Data Retention
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Free app for downloading and running local models, showing whether a quantization fits your GPU. Used to run Qwen3.8 in chat and serve it to other harnesses.
Similar AI tools
Closest neighbours by meaning, not just by category.
Spark-X2.6-1.7B
Model
Compact 1.7B open-weights text LLM for on-device use, with adjustable thinking levels and English/Chinese support.
GLM 5.3 Flash
Model · Zhipu AI
Zhipu AI's GLM-5.3-Flash, a fast open-weights LLM for coding and agentic tasks, available via Z.ai chat and API.
Muse Spark 1.2
Model · Meta
Closed-source Meta model for coding and agentic workflows with 1M-token context and multimodal input, offered via API.
Ollama
App · Ollama
Runs open AI models locally on macOS, Windows and Linux, with an optional paid cloud service for larger models.
Gemma
Model · Google
Google DeepMind's family of open-weights models built from Gemini technology, from phone-sized to laptop-class variants.
MiniCPM5 1B
Model · OpenBMB
1B-parameter dense open-weights language model from OpenBMB for on-device use, with hybrid thinking and 128K context.
