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
이 공급업체 계약서를 다섯 개 항목으로 요약해 주세요.
주요 조건은 다음과 같습니다: 24개월 계약 기간, 60일 후 지급, 그리고…
GPU 1개 · VRAM 48 GiB
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.

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.

gpt-oss:120b
OpenAI gpt-oss
GPU 1개 · VRAM 40 GiB

gemma4:31b
Google Gemma 4
GPU 1개 · VRAM 48 GiB

qwen3.6:27b
Qwen 3.6
GPU 1개 · VRAM 48 GiB

deepseek-r1:32b
DeepSeek-R1
GPU 1개 · VRAM 64 GiB
CPU 체험gemma4:e4b
Google Gemma 4
GPU 1개 · VRAM 16 GiB
CPU 체험qwen3.5:9b
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.
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.
작동 방식
From a model’s name to your own LLM in four steps.

gemma4:31b
Ollama 기반 Open WebUI
실행 위치
- Grid가 조건에 맞는 GPU를 찾았습니다
- 모델 다운로드 완료, 채팅 준비 완료
- HTTPS 주소 활성화됨
예시
Choose one from the App Gallery, or name any Ollama model. Each shows the GPU memory and disk it needs.
Your Kinesis Grid: Kinesis capacity, your cloud accounts or your own servers, under the max price per GPU-hour you set.
Quick Launch starts it as it is. Customize First opens every setting: environment variables, hardware and location.
Your Grid finds the GPU and downloads the model. Then the chat and the API answer on their own HTTPS addresses.
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 prompts go to your own app, on a GPU in your Kinesis Grid, and never to a model vendor. Your Grid never places work on community hardware unless you choose Kinesis Batches. For a deployment isolated for you, or one fully inside your own data center, see Kinesis Private.
아니요. Kinesis Grid는 Kinesis 용량, API 키로 연결한 클라우드 계정, 직접 보유한 서버를 원하는 대로 조합해 사용할 수 있습니다. 약 90억 파라미터 이하의 작은 모델은 서버리스 CPU에서 체험해 볼 수도 있습니다.
Yes. Each model template also serves the Ollama API on its own HTTPS port, with OpenAI-compatible endpoints under /v1. Point your SDK, agent framework or coding tool at that base URL.
Anyone with the app’s HTTPS address can reach it, and the chat and the API start without a sign-in. Before you share it, limit the app to your own IP addresses, or turn on the chat’s sign-in and put your own gateway in front of the API.
You pay for the GPU your model runs on, by the GPU-hour, never per token, and a spot GPU never costs more than the max price you set. For compute you bring, Kinesis charges a small Grid fee instead. The details are on our pricing page.
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.