Vai al contenuto
Unisciti al nostro server Discord
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.

La tua Kinesis Grid

Open WebUIgemma4:31b

Riassumi questo contratto con il fornitore in cinque punti.

Ecco i termini principali: durata di 24 mesi, pagamento a 60 giorni e…

1 GPU · 48 GiB di VRAM

API di un fornitore di modelli

Risposta da una GPU della tua Kinesis Grid.Nulla è arrivato a un fornitore di modelli.

Illustrativo

Perché privato

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 di un fornitore di modelli: 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 di un fornitore di modelli: 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 di un fornitore di modelli: Only the settings the vendor offers.Your private LLM: Your system prompt, your documents, your fine-tuned weights.
  • LimitsAPI di un fornitore di modelli: Shared rate limits and token quotas.Your private LLM: A GPU of its own, with no token quota.
  • Dove giraAPI di un fornitore di modelli: Wherever the vendor runs it.Your private LLM: The cloud, region or server you choose.
  • FatturazioneAPI di un fornitore di modelli: 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.

LLM open, ognuno con la propria chat privata

Open WebUI, una chat in stile ChatGPT, su Ollama: già configurata per te, sulle GPU della tua Grid.

  • Scheda della App Gallery per scegliere qualsiasi modello Ollama

    Scegli modello personalizzato

    Qualsiasi modello della libreria Ollama

    Cerca per nome, scegli una dimensione fino a 130 miliardi di parametri e Kinesis dimensiona la memoria GPU di conseguenza. Llama, Mistral, Phi e il resto della libreria.

  • Scheda della App Gallery per OpenAI gpt-oss

    gpt-oss:120b

    OpenAI gpt-oss

    1 GPU · 40 GiB di VRAM

  • Scheda della App Gallery per Google Gemma 4

    gemma4:31b

    Google Gemma 4

    1 GPU · 48 GiB di VRAM

  • Scheda della App Gallery per Qwen 3.6

    qwen3.6:27b

    Qwen 3.6

    1 GPU · 48 GiB di VRAM

  • Scheda della App Gallery per DeepSeek-R1

    deepseek-r1:32b

    DeepSeek-R1

    1 GPU · 64 GiB di VRAM

  • Scheda della App Gallery per Google Gemma 4Prova su CPU

    gemma4:e4b

    Google Gemma 4

    1 GPU · 16 GiB di VRAM

  • Scheda della App Gallery per Qwen 3.5Prova su CPU

    qwen3.5:9b

    Qwen 3.5

    1 GPU · 16 GiB di VRAM

Nella galleria c'è anche Microsoft BitNet su llama.cpp, che non richiede GPU. I modelli contrassegnati con Prova su CPU possono partire anche su CPU serverless; quelli più grandi girano su una GPU della tua Grid.

Cambia modello quando ne esce uno migliore: Gemma 4, Qwen 3.5 e Qwen 3.6 sono entrati nella galleria man mano che venivano rilasciati.

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.

gemma4:31bIn esecuzione

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"}]}'

Illustrativo

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.

  • Operativo in pochi minuti

    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.

  • Condiviso con il tuo team

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

  • Pronto per i tuoi agenti

    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.

Domande

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.