EF

Enflame Cloud Blazer POD P2010

rack
32× Yunsui T20
Two 200Gb/s links between compute nodes, as filed. The prospectus describes the cabinet as four to eight AI servers and several network switches joined by high-speed cabling; it gives no scale-up fabric for the accelerators.
Power
kW Total
Memory
1024
GB Total

Enflame's single-cabinet training appliance, branded Cloud Blazer POD and described in the company's STAR Market prospectus as a single-cabinet, single-compute-node device that forms the smallest unit of a compute cluster. It integrates 32 Yunsui T20 accelerators across four to eight AI servers, each server carrying eight cards. The filing lists it for training, air-cooled, with a PUE of 1.30 or better for the inference model and 1.25 or better for this one. Its 1TB of accelerator memory matches 32 cards at 32 GB exactly. Enflame publishes no throughput figure for this product or for the cards inside it.

We will point you at suppliers who have it. Free, and no signup.

System Details

GPU Configuration

GPU Count: 32 GPUs
Architecture: GCU / DTU 2.0
Interconnect: Two 200Gb/s links between compute nodes, as filed. The prospectus describes the cabinet as four to eight AI servers and several network switches joined by high-speed cabling; it gives no scale-up fabric for the accelerators.

System Specifications

Form Factor: rack
Total Power:
Total Memory: 1024 GB
Memory Bandwidth:

Powered by Enflame Yunsui T20

This system utilizes 32 × Enflame Yunsui T20 GPUs, each delivering exceptional performance for AI and HPC workloads.

Per GPU TDP

300W

Per GPU Memory

32 GB

Process Node

GlobalFoundries 12nm

Architecture

GCU / DTU 2.0

Documentation & Resources

Official Datasheet

Enflame Cloud Blazer POD P2010 technical specifications

Download PDF

Typical Use Cases

AI/ML Training
High-Performance Computing
Data Analytics

The Enflame Cloud Blazer POD P2010 runs 32× Yunsui T20 GPUs over Two 200Gb/s links between compute nodes, as filed. The prospectus describes the cabinet as four to eight AI servers and several network switches joined by high-speed cabling; it gives no scale-up fabric for the accelerators..