본문으로 건너뛰기
Discord 서버 참여하기
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.

내 Kinesis Grid

Open WebUIgemma4:31b

이 공급업체 계약서를 다섯 개 항목으로 요약해 주세요.

주요 조건은 다음과 같습니다: 24개월 계약 기간, 60일 후 지급, 그리고…

GPU 1개 · VRAM 48 GiB

모델 공급업체의 API

내 Kinesis Grid의 GPU가 응답했습니다.모델 공급업체로 전송된 내용은 없습니다.

예시

왜 프라이빗인가

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 data모델 공급업체의 API: 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 model모델 공급업체의 API: The vendor changes or retires it on its own schedule.Your private LLM: The model you picked, until you choose to switch.
  • Making it yours모델 공급업체의 API: Only the settings the vendor offers.Your private LLM: Your system prompt, your documents, your fine-tuned weights.
  • Limits모델 공급업체의 API: Shared rate limits and token quotas.Your private LLM: A GPU of its own, with no token quota.
  • 실행 위치모델 공급업체의 API: Wherever the vendor runs it.Your private LLM: The cloud, region or server you choose.
  • 청구모델 공급업체의 API: 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.

각자 프라이빗 채팅을 갖춘 오픈 LLM

ChatGPT 스타일의 채팅인 Open WebUI를 Ollama 위에, 내 Grid의 GPU에 설정해 드립니다.

  • 원하는 Ollama 모델을 고르는 App Gallery 카드

    사용자 지정 모델 선택

    Ollama 라이브러리의 모든 모델

    이름으로 검색하고 최대 1,300억 파라미터까지 크기를 고르면, Kinesis가 그에 맞게 GPU 메모리를 할당합니다. Llama, Mistral, Phi를 비롯한 라이브러리의 모든 모델을 쓸 수 있습니다.

  • OpenAI gpt-oss의 App Gallery 카드

    gpt-oss:120b

    OpenAI gpt-oss

    GPU 1개 · VRAM 40 GiB

  • Google Gemma 4의 App Gallery 카드

    gemma4:31b

    Google Gemma 4

    GPU 1개 · VRAM 48 GiB

  • Qwen 3.6의 App Gallery 카드

    qwen3.6:27b

    Qwen 3.6

    GPU 1개 · VRAM 48 GiB

  • DeepSeek-R1의 App Gallery 카드

    deepseek-r1:32b

    DeepSeek-R1

    GPU 1개 · VRAM 64 GiB

  • Google Gemma 4의 App Gallery 카드CPU 체험

    gemma4:e4b

    Google Gemma 4

    GPU 1개 · VRAM 16 GiB

  • Qwen 3.5의 App Gallery 카드CPU 체험

    qwen3.5:9b

    Qwen 3.5

    GPU 1개 · VRAM 16 GiB

갤러리에는 GPU가 필요 없는 llama.cpp 기반 Microsoft BitNet도 있습니다. CPU 체험 표시가 있는 모델은 서버리스 CPU에서도 시작할 수 있으며, 더 큰 모델은 내 Grid의 GPU에서 실행됩니다.

더 나은 모델이 나오면 바꾸세요. Gemma 4, Qwen 3.5, Qwen 3.6은 출시되자마자 갤러리에 추가되었습니다.

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.

gemma4:31b실행 중

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"}]}'

예시

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.

  • 몇 분 만에 가동

    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.

  • 팀과 공유

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

  • 에이전트도 바로 사용

    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.

질문

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.