Intel Gaudi 3 HLB-325 Baseboard
Intel's eight-accelerator universal baseboard for Gaudi 3, and the unit Intel offers OEMs to build servers around. It carries eight HL-325L OAM mezzanine cards and connects them all-to-all at 4.2 TB/s bidirectional without a switching chip, which is the design's distinguishing choice: scale-up needs no switch silicon, and scale-out runs over standard Ethernet at 1.2 TB/s through six OSFP connectors rather than a proprietary fabric. Intel rates the whole assembly at 7.6 kW including the eight OAMs, draws it from a 54 V main input with 12 V standby, and sizes the board at 417 by 585 mm to drop into 19-inch server designs. Sold either as the bare HLB-325 or, as the HLFB-325L, pre-populated with eight cards and tested as one subsystem. Intel publishes no aggregate throughput figure for the baseboard, so none is shown: per-accelerator compute is on the Gaudi 3 chip entry, sourced to Table 5 of Intel's technical paper. Total memory of 1.024 TB is the eight cards' published 128 GB apiece.
We will point you at suppliers who have it. Free, and no signup.
Systems built on this design
1 configurationIntel Gaudi 3 HLB-325 Baseboard is the baseboard. The systems above are OEM implementations of it and share its accelerator performance; they differ in chassis, CPU, memory and cooling.
System Details
GPU Configuration
System Specifications
Powered by Intel Gaudi 3
This system utilizes 8 × Intel Gaudi 3 128GB GPUs, each delivering exceptional performance for AI and HPC workloads.
Per GPU TDP
900W
Per GPU Memory
128 GB
Process Node
5nm
Architecture
Gaudi 3
Documentation & Resources
Official Datasheet
Intel Gaudi 3 HLB-325 Baseboard technical specifications
Intel to Expand AI Accelerator Portfolio with New GPU (Crescent Island announcement)
Intel • 2025-10-14
Typical Use Cases
The Intel Gaudi 3 HLB-325 Baseboard runs 8× Gaudi 3 GPUs over Direct all-to-all between the eight accelerators at 4.2 TB/s bidirectional with no switching IC, plus 1.2 TB/s bidirectional scale-out over 6 OSFP connectors as 24x 200 Gbps RDMA (RoCE v2); host attach is 8x PCIe Gen 5.0 x16.