Skip to main content
Version: 2.0

BYO-GPU Requirements

This guide covers the requirements and infrastructure needed to deploy Smart Studio on your own local IDC (Internet Data Center) with your GPU cluster.

Standard Requirements for IDC Deployment

The following CPU and storage servers are required. These servers must be on the same local virtual network as the GPUs.

No.Basic Server ConfigurationQuantityPurpose
1CPU: 64 cores, Memory: 128GB, Storage: 1T+3Deploy the Kubernetes control plane and Smart Studio platform services (required)
2GPU: depends on the local GPU configuration of the customer and the size of the LLMNSee the Minimum Configuration for Different Model Deployments

Demo of Network Topology


Minimum Requirements for IDC Deployment (POC)

For a minimal proof-of-concept setup, a single GPU server can be used.

No.Basic Server ConfigurationQuantityPurpose
1GPU: H20/H100/H200/RTX PRO 6000, CPU: 128+ cores, Memory: 1TB, Storage: 1T+1All services — Kubernetes control plane, CNI, Smart Studio platform, and Model Serving deployed on one GPU server (without HA guarantee)

Demo of Network Topology


Minimum Configuration for Different Model Deployments

You can provide your required model name to us, and we will respond with the GPU requirements.

ModelMinimum Deployment GPU Specification (Estimated)Memory Pool Base Scale
Qwen3.6-27B (FP8) / Qwen3.6-35B-A3B (FP8)1 Card: H20-96G, H20-141G, A800-80G, or equivalent ≥80G VRAM per card.etc
2 Cards: L20-48G, L40s-48G, or equivalent ≥48G VRAM per card.etc
>1.5T
Qwen3.5-397B-A22B (FP8)4 Cards: ≥188G VRAM per card
8 Cards: H20-96G, H20-141G, or equivalent ≥80G VRAM per card.etc
>4T
Deepseek V4-Flash4 Cards: H20-96G, H20-141G, RTX PRO 6000-96G, or equivalent ≥80G VRAM per card.etc>1T
GLM-5.2 (FP8)4 Cards: ≥288G VRAM per card
8 Cards: H20-141G, or equivalent ≥141G VRAM per card.etc
16 Cards: H20-96G, or equivalent ≥80G VRAM per card.etc
>8T
Qwen3.7-Plus8 Cards: H20-141G, H20-96G, or equivalent ≥ 80G VRAM per card.etc (8 Cards is preferred)>4T
Qwen3.7-Max8 Cards: ≥288G VRAM per card>15T
Note
  • Estimations for Qwen3.7-Plus/Max are based on FP8 dtype and may not be fully accurate.
  • You are responsible for providing the required GPU resources (purchased or self-owned), as the platform does not include them.
  • For more technical details about deployment or other model deployment configurations, please contact us.

Diagram of Infrastructure to Deploy Smart Studio on Local IDC

GPU/CPU infrastructure → Scheduler and Model Serving → Smart Studio control plane

Next Step

Once your infrastructure meets the requirements above, proceed to Activate Cluster to connect your servers and deploy the Smart Studio platform.