Models & inference
LM Studio
Desktop apps for running open LLMs locally, with a local API server and Bionic, an agent for documents, code and automation.
What LM Studio does
LM Studio makes desktop software for running open language models on your own computer. The company now offers two apps. LM Studio is the original one: a chat interface plus a programmable API for downloading and running models. LM Studio Bionic is a newer agent app that creates and edits documents, slides, PDFs and code, and can handle automations and computer control.
Both run models locally through the LM Studio runtime, which uses llama.cpp for GGUF models and Apple's MLX on Apple Silicon Macs. The docs list support for Apple Silicon Macs, x64 and ARM64 Windows PCs, and x64 Linux. You can chat with documents offline, add MCP servers for local models, and download models from Hugging Face inside the app. Bionic also transcribes speech in real time on the device.
For developers, LM Studio serves models over a local REST API with OpenAI-compatible and Anthropic-compatible endpoints. There are TypeScript (lmstudio-js) and Python (lmstudio-python) SDKs, an lms command-line tool, and llmster, a headless daemon for servers, cloud instances and CI.
The free plan covers local models. Paid Bionic plans add US-hosted open models such as Kimi K3 and GLM 5.3, which LM Studio says run under zero data retention. It suits people who want to run open models privately on their own hardware, and developers who want a local OpenAI-style endpoint for testing apps.
- Chat with an open model running entirely on your own computer.
- Ask questions about attached documents offline.
- Serve a local model on an OpenAI-compatible or Anthropic-compatible endpoint for app development.
- Run models headless on a server or in CI with llmster.
- Use the Bionic agent to draft and edit documents, slides and code.
Who should use it
- People who want to run open models locally for privacy.
- Developers who need a local OpenAI-style API for testing.
Who should look elsewhere
- Intel Mac users, since the docs list Apple Silicon for macOS.
- Teams that need team subscription plans now, which LM Studio lists as coming soon.
Strengths
- Local inference with llama.cpp and MLX, with downloads from Hugging Face in the app.
- Local server with OpenAI- and Anthropic-compatible endpoints plus JS and Python SDKs.
- Headless llmster daemon for servers and CI.
- Privacy policy says local chats and documents are never transmitted off the device.
Limitations
- Local performance depends on your hardware.
- MLX models run only on Apple Silicon Macs.
- Hosted models in paid plans come with usage limits, and extra use needs cloud credits.
- Team subscription plans are not yet offered; only centralized billing through organizations.
Privacy notes
LM Studio's privacy policy says messages, chat histories and documents are never transmitted when models run locally. For its cloud services, requests and responses are not retained after the request completes and are not used for training.
Sources
- Welcome to LM Studio Docs! | LM StudioOfficial docsPrimarylmstudio.ai
- lmstudio.ai/docs/developerWeb
- LM Studio Bionic - Agent for Work and CodeOfficial sitePrimarylmstudio.ai
- Bionic Pricing | LM StudioPricing pagePrimarylmstudio.ai
- LM Studio Docs | LM StudioOfficial docsPrimarylmstudio.ai
- lmstudio.ai/downloadWeb
- lmstudio.ai/app-privacyWeb
LM Studio alternatives
PocketWebTools for Mac
Models & inference
Mac app that runs open AI models up to 35B parameters offline for chat, transcription, OCR, upscaling and video clipping.
PaidVerifiedej
Models & inference
An 11 MB open-weight model from HITL Systems that answers routing, yes/no and priority questions about text on CPU.
Open sourceVerifiedClef
Models & inference
Cloudflare's open-weight decision models that return typed answers with probabilities, hosted on Workers AI.
Open sourceFree tierAPIVerifiedLloyal
Models & inference
A TypeScript framework for AI apps that run an open-weight model inside the app, offline and without an API key.
Open sourceFree tierVerifiedReplicate
Models & inference
A cloud API for running, fine-tuning and deploying open-source and proprietary AI models, billed by usage.
PaidAPIVerifiedOllama
Models & inference
An open-source tool and API for running open models on your own machine or on Ollama's cloud.
Open sourceFree tierAPIVerified
Related open-source projects
oMLX is a local LLM inference server for Macs with Apple Silicon, built on MLX and managed from a menu bar app. It exposes OpenAI-compatible and Anthropic-compatible endpoints, so existing clients can connect to http://localhost:8000/v1 without code changes. Its main idea is a two-tier KV cache. Frequently used cache blocks stay in RAM, and when that hot tier fills up, blocks are offloaded to the SSD in safetensors format so they can be reused instead of recomputed. The author pitches this at long coding sessions with tools such as Claude Code. Concurrent requests go through continuous batching using mlx-lm's BatchGenerator. The server loads text LLMs, vision-language models, OCR models, embeddings and rerankers. Several models can stay loaded at once, with least-recently-used eviction, pinning and a per-model idle timeout. A web admin dashboard at /admin covers monitoring, model management, chat and benchmarks. Source builds also include an experimental mode that splits one model across several Macs. You can install it as a .dmg from GitHub Releases, through Homebrew, or from source, and it is licensed under Apache-2.0.
- Stars
- 23K
- Language
- Python
- License
- Apache-2.0
- Momentum
- Established
llmfit is a terminal tool, written in Rust, that inspects your hardware and tells you which open-source large language models it can run well. It detects CPU cores, system RAM, GPUs, VRAM and unified memory (NVIDIA CUDA, Apple Silicon, AMD ROCm and Intel OneAPI), then estimates memory use and tokens per second for each model across quantizations. Each model gets scores for quality, speed, fit and context, plus a fit verdict that runs from Perfect to Too Tight. The default interface is an interactive TUI. A classic CLI mode, a web dashboard and a REST API (/api/v1/system and /api/v1/models) are also available. llmfit works with Ollama, llama.cpp, MLX, Docker Model Runner and LM Studio, and can download a chosen model through them. Speed figures come from a memory-bandwidth formula unless a measurement exists. A newer benchmark feature measures real tok/s on your machine and lets you submit the result to the project as a pull request from the TUI, so later releases carry measured numbers for matching hardware. The tool runs on macOS, Linux and Windows and is MIT licensed. The latest release is v1.1.17.
- Stars
- 38K
- Language
- Rust
- License
- MIT
- Momentum
- Established
iFixAi is an open-source Python tool that audits AI agents and models by running a set of test inspections and returning an A to F grade with a written report. The free engine has 60 inspections. The grade comes from five core pillars: fabrication, manipulation, deception, unpredictability and opacity. Another 28 inspections from twenty premium categories are included and reported on their own, outside the grade. A grade counts as citable only when a judge model from a different vendor scores the run, so a full audit needs two API keys. You can test a bare model through providers such as Anthropic, OpenAI, Gemini, Azure, Bedrock and OpenRouter, or point the tool at your own agent's OpenAI-compatible HTTP endpoint. There are three ways to run it: a setup wizard, a CLI with explicit flags for CI, or a plugin for Claude Code and Codex, with a scaffolded /ifixai-skill command for other agents. Reports land as JSON and Markdown in ./ifixai-results/. The README estimates judge costs for a full run with a Sonnet judge at roughly $12 to $18, billed by the provider. The company also sells iFixAi Pro, a paid audit service with up to 400 inspections. Telemetry is on by default outside CI and can be switched off.
- Stars
- 24K
- Language
- Python
- License
- Apache-2.0
- Momentum
- Established
AI Engineering from Scratch is a free, MIT-licensed course on GitHub that teaches how AI systems work by having you write each piece yourself, starting with linear algebra and ending with multi-agent systems and production infrastructure. The material is split into 20 phases and 523 lessons, with code in Python, TypeScript, Rust and Julia. Each lesson folder holds a written explanation, runnable code and an outputs directory. The pattern is to build an algorithm such as backpropagation, a tokenizer, attention or an agent loop from plain math first, and only then run the same idea through a library like PyTorch or scikit-learn. Lessons end with something you keep: a prompt, a SKILL.md file, an agent or an MCP server. The repository holds 396 skills and 99 prompts produced this way, plus a script that copies them into an agent's skills folder. There are three ways to follow it. You can read lessons on the website with no setup, clone the repository and run the code locally, or install the course's tutor skills into a coding agent such as Claude Code or Codex. Those skills run a placement quiz, write a study plan to LEARNING.md and teach one lesson per session. Separate tracks prepare for the four Claude certification exams and the MCP Associate exam; the README says these are independent and not affiliated with the exam bodies.
- Stars
- 68K
- Language
- Python
- License
- MIT
- Momentum
- +8.2% 7dEstablished
Related guides
- ComparisonModels & inference
llama.cpp vs Ollama vs LM Studio: which local model runner fits your setup
Compare llama.cpp vs Ollama vs LM Studio on APIs, GPU and OS support, model formats and licences, then pick a local model runner with a decision table.
7 min read
- TutorialModels & inference
Fine tune LLM LoRA adapters: data, training and a first test on one GPU
Fine tune LLM LoRA adapters on one GPU: check that fine-tuning fits, prepare data, train with PEFT and TRL or Unsloth, and compare against the base model.
6 min read
- NewsModels & inference
NVIDIA releases Nemotron 3.5 Super VL and a 24GB Bolt model for local agents
NVIDIA released Nemotron 3.5 Super VL, a 120B open vision model, and Bolt 74B-A9B for 24GB local use. What developers can run now and what is missing.
4 min read
- Weekly digest
This week on HuiaHub: local models, MCP guides and 18 new videos
Local LLMs with Ollama and vLLM, MCP servers in Python, Claude Code hooks, 18 talks and new agent skills: everything HuiaHub published so far.
4 min read
- News
NVIDIA adds a 64GB DGX Spark for local AI, with two-unit clustering
NVIDIA's DGX Spark gets a 64GB configuration at $4,999 from six partners, plus two-unit clustering. What changes for local AI developers.
4 min read