LM Studio — interface graphique de bureau pour LLM en local (Windows · Mac · Linux)

Quick Start — Desktop Install and Local Server

L’onglet Developer expose le serveur local — par défaut, il calque l’endpoint chat completions d’OpenAI sur /v1. La CLI lms est distribuée séparément (brew install lmstudio-cli sur macOS) et reste optionnelle pour les utilisateurs GUI. Le RAG sur documents locaux vit dans l’onglet Chat → « My Documents » depuis la v0.3.

# 1. Install the desktop app
#    https://lmstudio.ai/download  (macOS, Windows, Linux)

# 2. Inside LM Studio:
#    - Open the "Discover" tab → search "Llama 3.2"
#    - Pick a quantization (Q4_K_M is a good default for ~8GB RAM)
#    - Click "Download"
#    - Open the "Chat" tab → select the model → chat

# 3. Start the local server (inside LM Studio → "Developer" tab → "Start Server")
#    Or from the CLI (requires "lms" installed):
lms server start --port 1234

# 4. Use any OpenAI SDK with base_url http://localhost:1234/v1
python - <<'PY'
from openai import OpenAI
client = OpenAI(base_url="http://localhost:1234/v1", api_key="lm-studio")
r = client.chat.completions.create(
    model="lmstudio-community/Llama-3.2-3B-Instruct-GGUF",
    messages=[{"role":"user","content":"One tip for learning Rust?"}],
)
print(r.choices[0].message.content)
PY

# Automation: script model management from the terminal
lms ls                              # list local models
lms load llama-3.2-3b-instruct      # load a specific model
lms unload --all                    # free VRAM

Fonctionnalités clés

Comparaison

Cas d'usage

Tarification et licence

Assets associés sur TokRepo

SillyTavern — LLM Frontend for Power Users

A self-hosted chat interface for interacting with local and cloud LLMs, featuring character cards, group chats, extensions, and advanced prompt management.

Prompt Flow — Build, Test & Deploy LLM Pipelines

Prompt Flow by Microsoft provides a visual editor and CLI for building LLM application workflows with built-in evaluation, tracing, and CI/CD integration for production deployment.

Gorilla — LLM That Writes Accurate API Calls

Gorilla is a fine-tuned LLM from UC Berkeley that generates correct API calls with reduced hallucination. It connects language models to thousands of real-world APIs and tools.

LMMS — Free Cross-Platform Digital Audio Workstation

LMMS (Linux MultiMedia Studio) is a free, open-source digital audio workstation for music production. It includes synthesizers, sample playback, beat sequencing, and an effects chain, providing a complete environment for creating music without any cost.

Questions fréquentes