> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hellocobi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Requirements

> Hardware, software, and access requirements for deploying Cobi on-premises

## CLI Tools

Install these on the machine you will run Helm from:

| Tool      | Minimum version | Install                                                  |
| --------- | --------------- | -------------------------------------------------------- |
| `kubectl` | 1.28+           | [kubernetes.io](https://kubernetes.io/docs/tasks/tools/) |
| `helm`    | 3.12+           | [helm.sh](https://helm.sh/docs/intro/install/)           |

## Cluster Requirements

### Kubernetes

| Property           | Requirement                                         |
| ------------------ | --------------------------------------------------- |
| Kubernetes version | 1.28+                                               |
| CNI                | Any (Calico, Cilium, Flannel, etc.)                 |
| Ingress controller | `ingress-nginx` (IngressClass `nginx`)              |
| Storage            | A default StorageClass with `ReadWriteOnce` support |

### OpenShift

| Property          | Requirement                                            |
| ----------------- | ------------------------------------------------------ |
| OpenShift version | 4.12+                                                  |
| Ingress           | OpenShift Router (built-in)                            |
| Storage           | Default StorageClass with `ReadWriteOnce` support      |
| SCC               | `anyuid` SCC for pods that need it (PostgreSQL, MinIO) |

## Node Sizing

### Without GPU inference (vLLM disabled)

| Component         | CPU request  | Memory request | Storage         |
| ----------------- | ------------ | -------------- | --------------- |
| backend           | 250m         | 512Mi          | —               |
| frontend          | 100m         | 256Mi          | —               |
| dashboard-connect | 100m         | 256Mi          | —               |
| postgresql        | 250m         | 512Mi          | 10 Gi PVC       |
| qdrant            | 500m         | 1Gi            | 10 Gi PVC       |
| minio             | 250m         | 512Mi          | 100 Gi PVC      |
| otel-lgtm         | 500m         | 1Gi            | 25 Gi PVC total |
| **Total**         | **\~2 vCPU** | **\~5 Gi**     | **\~145 Gi**    |

A single node with **4 vCPU / 8 Gi RAM** and **200 Gi** available disk is sufficient for a minimal deployment.

### With GPU inference (vLLM enabled)

The vLLM pod must be scheduled on a GPU node. The recommended model (Qwen3.5-9B-AWQ) requires:

| Resource             | Minimum                       | Recommended                                             |
| -------------------- | ----------------------------- | ------------------------------------------------------- |
| GPU                  | 1× NVIDIA GPU with 16 Gi VRAM | 1× A10G 24 Gi (e.g. `g5.2xlarge` or on-prem equivalent) |
| CPU                  | 4 vCPU                        | 8 vCPU                                                  |
| RAM                  | 20 Gi                         | 28 Gi                                                   |
| Disk (model weights) | 30 Gi                         | 80 Gi PVC                                               |
| NVIDIA driver        | 525+                          | 535+                                                    |
| CUDA                 | 11.8+                         | 12.x                                                    |

<Note>
  The GPU node must run the **NVIDIA device plugin** DaemonSet so `nvidia.com/gpu` is visible as a schedulable resource. See [GPU Setup](/deployment/gpu-setup).
</Note>

## Image Registry Access

All Cobi application images (`hellocobi/*`) are hosted on Docker Hub as private images. You need:

1. Docker Hub credentials with pull access to the `hellocobi` organization.
2. A Kubernetes Secret of type `kubernetes.io/dockerconfigjson` in the target namespace.

```bash theme={null}
kubectl create secret docker-registry dockerhub-secret \
  --docker-server=https://index.docker.io/v1/ \
  --docker-username=<username> \
  --docker-password=<password-or-token> \
  --docker-email=<email> \
  --namespace <your-namespace>
```

Reference it in your values file:

```yaml theme={null}
global:
  imagePullSecrets:
    - dockerhub-secret
```

## Hugging Face Token

vLLM downloads model weights from [huggingface.co](https://huggingface.co) at startup. You need a Hugging Face account and an access token with read access to the model repository:

* [Create a token](https://huggingface.co/settings/tokens) with `read` scope.
* Pass it via `vllmstack.servingEngineSpec.modelSpec[0].hf_token` in your values file.
* For air-gapped clusters, pre-download the model weights and serve them from a local cache volume.

## Persistent Storage

All stateful components use `ReadWriteOnce` PersistentVolumeClaims. The default StorageClass is used unless you specify `storageClass` in each component's values.

For on-premises clusters without a cloud storage provisioner, common options are:

| Provisioner             | Notes                                              |
| ----------------------- | -------------------------------------------------- |
| `rancher.io/local-path` | Single-node dev/staging; data is local to the node |
| `nfs.csi.k8s.io`        | Multi-node HA; requires an NFS server              |
| OpenEBS                 | Block storage for bare-metal clusters              |
| Longhorn                | Distributed block storage for bare-metal clusters  |

Set the storage class globally per component:

```yaml theme={null}
postgresql:
  primary:
    persistence:
      storageClass: "local-path"

qdrant:
  persistence:
    storageClass: "local-path"

minio:
  persistence:
    storageClass: "local-path"
```