Zum Inhalt springen
Treten Sie unserem Discord-Server bei
Kinesis

Private LLM

Your own LLM. A few clicks away.

Run any open model from the App Gallery as your private chat and API, on a GPU your Kinesis Grid finds and keeps running.

Ihr Kinesis Grid

Open WebUIgemma4:31b

Fasse diesen Liefervertrag in fünf Stichpunkten zusammen.

Hier die wichtigsten Konditionen: 24 Monate Laufzeit, Zahlungsziel 60 Tage und…

1 GPU · 48 GiB VRAM

API eines Modellanbieters

Beantwortet von einer GPU in Ihrem Kinesis Grid.Nichts ging an einen Modellanbieter.

Beispielhaft

Warum privat

A model of your own beats a model you rent by the token.

Frontier APIs are great for the hardest problems. For everyday work on your own data, a private model gives you control.

  • Your dataAPI eines Modellanbieters: Prompts and documents go to the vendor, under its terms for keeping them.Your private LLM: Prompts stay with your app, on a GPU in your Kinesis Grid.
  • The modelAPI eines Modellanbieters: The vendor changes or retires it on its own schedule.Your private LLM: The model you picked, until you choose to switch.
  • Making it yoursAPI eines Modellanbieters: Only the settings the vendor offers.Your private LLM: Your system prompt, your documents, your fine-tuned weights.
  • LimitsAPI eines Modellanbieters: Shared rate limits and token quotas.Your private LLM: A GPU of its own, with no token quota.
  • AusführungsortAPI eines Modellanbieters: Wherever the vendor runs it.Your private LLM: The cloud, region or server you choose.
  • AbrechnungAPI eines Modellanbieters: Per token: the bill grows with every question.Your private LLM: Per GPU-hour, however much your team asks.

Any model

Pick a model, or name any other.

The App Gallery has the leading open models ready to launch, and a picker for the whole Ollama library.

Offene LLMs, jedes mit eigenem privatem Chat

Open WebUI, ein Chat im Stil von ChatGPT, auf Ollama: für Sie eingerichtet, auf GPUs in Ihrem Grid.

  • Karte in der App Gallery zur Auswahl eines beliebigen Ollama-Modells

    Eigenes Modell wählen

    Jedes Modell aus der Ollama-Bibliothek

    Suchen Sie nach Namen, wählen Sie eine Größe bis 130 Mrd. Parameter, und Kinesis bemisst den GPU-Speicher passend dazu. Llama, Mistral, Phi und der Rest der Bibliothek.

  • Karte für OpenAI gpt-oss in der App Gallery

    gpt-oss:120b

    OpenAI gpt-oss

    1 GPU · 40 GiB VRAM

  • Karte für Google Gemma 4 in der App Gallery

    gemma4:31b

    Google Gemma 4

    1 GPU · 48 GiB VRAM

  • Karte für Qwen 3.6 in der App Gallery

    qwen3.6:27b

    Qwen 3.6

    1 GPU · 48 GiB VRAM

  • Karte für DeepSeek-R1 in der App Gallery

    deepseek-r1:32b

    DeepSeek-R1

    1 GPU · 64 GiB VRAM

  • Karte für Google Gemma 4 in der App GalleryTest auf CPU

    gemma4:e4b

    Google Gemma 4

    1 GPU · 16 GiB VRAM

  • Karte für Qwen 3.5 in der App GalleryTest auf CPU

    qwen3.5:9b

    Qwen 3.5

    1 GPU · 16 GiB VRAM

Ebenfalls in der Galerie: Microsoft BitNet auf llama.cpp, das keine GPU braucht. Modelle mit der Kennzeichnung „Test auf CPU“ können auch auf Serverless-CPU starten; größere laufen auf einer GPU in Ihrem Grid.

Wechseln Sie das Modell, wenn ein besseres erscheint: Gemma 4, Qwen 3.5 und Qwen 3.6 kamen jeweils mit ihrer Veröffentlichung in die Galerie.

Not in the gallery? Bring the model.

Deploy any container image, or build one from a GitHub repository or a Dockerfile. It runs on the same Grid, with the same HTTPS address, logs and metrics.

  • vLLM + Hugging Face
  • llama.cpp
  • Your fine-tuned weights

Chat and API

A chat for your team. An API for your code.

Every model comes with a ChatGPT-style chat and an OpenAI-compatible API, each on its own HTTPS address. Existing code only changes its base URL.

gemma4:31bLäuft

Chat for your team

https://your-app.apps.kinesiscloud.com

Open WebUI, a ChatGPT-style chat in the browser.

API for your code

https://your-app.apps.kinesiscloud.com:<port>/v1

OpenAI-compatible: point your SDK or tool at the new base URL.

$ curl https://your-app…/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{"model": "gemma4:31b",
         "messages": [{"role": "user",
                       "content": "Draft a reply to this ticket"}]}'

Beispielhaft

Why Kinesis

Everything around the model is already there.

A private LLM is more than a GPU and a model. Kinesis brings the rest.

  • The GPU, found for you

    Your Kinesis Grid finds a GPU that fits the model: Kinesis capacity, a cloud account you connect, or a server you own.

  • In wenigen Minuten live

    No drivers, no gateway, no certificates to set up. The chat and the API come up on their own HTTPS address.

  • Kept running

    If a machine fails or a spot GPU leaves, your Grid moves the model to another machine that fits.

  • Mit Ihrem Team geteilt

    Models live in your organization’s projects, with SSO, roles, logs and metrics.

  • Bereit für Ihre Agenten

    The REST API and MCP server can launch a model for you, from Claude, ChatGPT or Cursor.

  • Private all the way down

    Need more? Kinesis Private runs the whole platform isolated for you, or fully inside your own data center.

Fragen

What people ask about private LLMs.

The App Gallery has gpt-oss, Gemma 4, Qwen 3.5 and 3.6, DeepSeek-R1 and Microsoft BitNet ready to launch, and a picker for any model in the Ollama library, up to 130B parameters. For anything else, such as a Hugging Face model on vLLM or your own fine-tune, deploy a container image.

Your private LLM is a few clicks away.

Create an account, pick a model, and your Kinesis Grid finds the GPU and keeps it running.