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.

Keine Installation nötig – KI-Modelle in der Cloud ausführen

BitVector Prism ist der einfachste Einstieg: Modell wählen, Prompt eingeben und in einer übersichtlichen Web-App generieren, ohne etwas einzurichten. BitVector gibt es auch auf Discord und im Web (SpyGlass).

BitVector ausprobieren

Was du brauchst

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.

So bekommst und installierst du 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.

Lade nur über die offiziellen Links auf dieser Seite herunter. Installer von anderswo können veraltet oder manipuliert sein. ModelTrends.ai hostet keine Dateien.

Keine Installation nötig – KI-Modelle in der Cloud ausführen

PirateDiffusion gibt es nur auf Telegram und richtet sich an Profis: tausende Modelle, LoRAs und Workflows per Chat-Befehl, mit unbegrenzter Generierung zum Festpreis.

PirateDiffusion ausprobieren

So benutzt du 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.

Tipps und häufige Probleme

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.

Modelle, die du in LM Studio ausführen kannst

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.

Text / LLM-Modelle

Keine Installation nötig – KI-Modelle in der Cloud ausführen

Keine GPU, keine Downloads, kein Python. Diese Dienste führen dieselben Open-Source-Modelle auf ihren eigenen Servern aus, sodass du in einer Minute im Browser, auf Discord oder Telegram loslegen kannst.

BitVector ausprobieren

PirateDiffusion ausprobieren

Links

Diese Links führen zu den Seiten der Hersteller. ModelTrends.ai ist nicht mit ihnen verbunden und hostet keine Software.

Weitere lokale Apps

So installierst du 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.