LM Studio is a free desktop app for running large language models locally. It has a built-in search for models from Hugging Face in GGUF and MLX format, a chat interface with document attachment (RAG), and a local server that mimics the OpenAI API so other programs can use your local model. It runs fully offline once a model is downloaded.

LM Studio is the easiest way to try the text models listed in this catalog on your own machine, for people who want a polished interface and do not want to touch a terminal. Developers who prefer command line tools may like Ollama better.

Aucune installation requise – exécutez les modèles IA dans le cloud

BitVector Prism est la façon la plus simple de commencer : choisissez un modèle, tapez un prompt et générez dans une application web épurée, sans rien configurer. BitVector est aussi disponible sur Discord et sur le web (SpyGlass).

Essayer BitVector

Ce qu’il vous faut

Apple Silicon Mac with macOS 13.4 or later (16 GB RAM recommended), Windows 10 or 11 (x64 or ARM) or Linux with a processor supporting AVX2. An NVIDIA or AMD GPU speeds things up and allows larger models; 8 GB VRAM runs 7 to 8 billion parameter models comfortably. Models take 2 to 40 GB each.

Comment obtenir et installer LM Studio

Download LM Studio from lmstudio.ai for Mac, Windows or Linux and install it.
Open the app and go to Discover (the magnifying glass). Search for a model, for example Llama, Qwen or Gemma.
Pick a quantized version that fits your memory (Q4_K_M is the usual balance; LM Studio marks the ones that fit) and press Download.
Models download into the app's models folder; you can change the folder in My Models if you want them on another drive.

Téléchargez uniquement depuis les liens officiels de cette page. Les installateurs trouvés ailleurs peuvent être obsolètes ou modifiés. ModelTrends.ai n’héberge aucun fichier.

Aucune installation requise – exécutez les modèles IA dans le cloud

PirateDiffusion est réservé à Telegram et conçu pour les pros : des milliers de modèles, LoRA et workflows pilotés par commandes de chat, avec génération illimitée à prix fixe.

Essayer PirateDiffusion

Comment utiliser LM Studio

Open the Chat tab, click Select a model at the top and load the model you downloaded.
Type a message and press Enter. Responses stream in; use the sidebar to start new chats or switch models.
Set a system prompt and sampling settings (temperature, context length) in the right-hand panel to shape the behaviour.
Attach PDF or text files to a chat to ask questions about them (RAG), or paste images for vision-capable models.
Open the Developer tab and start the local server to use the model from other apps through an OpenAI-compatible API at http://localhost:1234.
Use My Models to see what is downloaded, delete models you no longer need and check their sizes.

Conseils et problèmes courants

If a model loads but answers slowly, choose a smaller quantization or offload fewer layers to the GPU in the model settings.
Set the context length only as long as you need; longer contexts use much more memory.
MLX models are fastest on Apple Silicon; GGUF works everywhere.
Nothing leaves your computer during chat; the only network use is downloading models.

Modèles utilisables dans LM Studio

LM Studio runs the open text models listed under Text / LLM in this catalog whenever a GGUF or MLX version exists on Hugging Face, which is the case for nearly all of them.

Modèles Text / LLM

Aucune installation requise – exécutez les modèles IA dans le cloud

Pas de GPU, pas de téléchargement, pas de Python. Ces services exécutent les mêmes modèles open source sur leurs propres serveurs : vous générez depuis un navigateur, Discord ou Telegram en une minute.

Essayer BitVector

Essayer PirateDiffusion

Liens

Ces liens mènent aux sites des éditeurs. ModelTrends.ai n’est pas affilié à eux et n’héberge aucun logiciel.

Autres applis locales

Comment installer ComfyUI

The node-based powerhouse for Stable Diffusion, Flux, Wan video and almost every new open source model. Free, open source, for Windows, Mac and Linux.