Loading products and specifications…
AI Server
Build around your workload
NVIDIA DGX B300. Gpu: 8 x NVIDIA B300 SXM6 GPUs, NVL8; 2.3 TB raw aggregate GPU memory; Form factor: 10U air-cooled rack server. Ask for current pricing and help choosing the right configuration.
Transaction requirements
Direct paying buyers only.
NVIDIA / PRODUCT DETAILS
See what is installed, then compare it with the platform limits. The maximum supported configuration may be different from what ships with this unit.
KEY SPECIFICATIONS / 01
Confirm drive carriers, backplane, controller and any required cables.
NVIDIA / ORDER & INSTALLATION DETAILS
Distinguish a GPU board, accelerator module and complete NVIDIA system.
Check the qualified host, original power arrangement and cooling.
Review the driver or compute stack and required interconnect components.
Technical overview
Use the full part number when comparing options or asking about system fit.
| Gpu | 8 x NVIDIA B300 SXM6 GPUs, NVL8; 2.3 TB raw aggregate GPU memory |
|---|---|
| Form factor | 10U air-cooled rack server |
| GPU subsystem | 8 × NVIDIA B300 |
| GPU memory | 2,304 GB aggregate (8 × 288 GB) |
| Cooling | Air cooling; AC or DC system variant |
| Power reference | 14.5 kW specified system power |
| Processor platform | 2 × Intel Xeon Platinum 6776P |
| System memory | 2 TB standard; up to 4 TB |
| Local storage | 8 × 3.84 TB E1.S NVMe data cache; 2 × 1.92 TB M.2 boot |
| Network fabric | 8 × ConnectX-8, up to 800 Gb/s |
| Manufacturer model / P/N | DGX B300 |
| Accelerator subsystem | 8 x NVIDIA B300 SXM6 GPUs, NVL8; 2.3 TB raw aggregate GPU memory |
| Network and I/O fabric | 8 x ConnectX-8 up to 800 Gb/s + 2 x dual-port BlueField-3 400 Gb/s DPUs |
| Power architecture | 14.5 kW maximum; 12 x 3.2 kW power modules |
| Manufacturer | NVIDIA |
| Model | DGX B300 |
| Model / P/N | NVIDIA DGX B300 |
| Category | AI Server |
| FABRIC | 8 x ConnectX-8 up to 800 Gb/s + 2 x dual-port BlueField-3 400 Gb/s DPUs |
| THERMAL | Air-cooled |
HOW THIS PRODUCT FITS YOUR SYSTEM
Choose how you plan to use this product.
Match the processor generation, socket population and required heatsink.
Check the installed modules, supported type and population rules.
Use this checklist to describe the change. The host system and full configuration determine which parts will fit.
YOUR QUOTE REQUEST
Add the quantity, options and installation details you want us to quote.
Confirm the exact manufacturer part number, host compatibility and included components. Optional software is quoted separately only when requested.
SUPPORT & REPLACEMENT
Check support dates, replacement options and whether continued use still makes sense.
We do not have confirmed sales and support dates for this part number.
Send us the full DGX B300 order code, software release and support details before planning long-term use.
Ask us to check the current sales and support statusProducts with similar names or connectors may still be incompatible. Compare the full specifications, installed system and software requirements.
Compare related products These products may be related, but we have not confirmed them as replacements.USING HARDWARE RESPONSIBLY
Consider repairability, remaining support and actual operating demand. Extending service life is useful only when the equipment still meets your security and reliability requirements.
Use measured average input power for the same workload. PSU ratings and processor TDP are different from total system power.
Energy difference = (current W − proposed W) × hours × units ÷ 1,000. Excludes cooling, embodied emissions and purchase costs.CONNECTION DETAILS
Choose the host adapters around the workload and the storage protocol. A server NIC, Fibre Channel HBA and SAS HBA serve different connections.
Browse the categories above for related equipment, then send us the full configuration so we can check the fit.
PRODUCT DETAILS
EXACT PLATFORM / SOURCE-REVIEWED SUMMARY
Aggregate GPU memory is the sum across installed GPUs, not one independently addressable memory pool. Actual configuration and supported options must be confirmed.
View office locationsWAREHOUSE SCENE STUDIES
Explore model-specific handling and packing scenarios with fully supported chassis, low industrial platforms and protective packaging. These are illustrative product-category images, not photographs of available stock. Review offered-unit photographs during the in-person transaction review.
| Manufacturer model / P/N | DGX B300 |
|---|---|
| Form factor | 10U air-cooled rack server |
| Processor platform | 2 x Intel Xeon Platinum 6776P |
| Accelerator subsystem | 8 x NVIDIA B300 SXM6 GPUs, NVL8; 2.3 TB raw aggregate GPU memory |
| System memory | 2 TB DDR5 system memory standard; up to 4 TB |
| Local storage | 8 x 3.84 TB E1.S NVMe + 2 x 1.92 TB M.2 boot |
| Network and I/O fabric | 8 x ConnectX-8 up to 800 Gb/s + 2 x dual-port BlueField-3 400 Gb/s DPUs |
| Power architecture | 14.5 kW maximum; 12 x 3.2 kW power modules |
| Cooling | Air-cooled |
Confirm option codes, firmware, region, lifecycle and the supplied configuration with your quotation. Transactions follow the direct-buyer and in-person meeting policy above.
model receiving and deployment photography
Server configuration
Accelerator, adapter or DPU; exact board code and supported host.
Switch or computing system; its own SKU, firmware and configuration.
Product and edition; deployment rights and support where applicable.
Where NVIDIA lists both a current SKU and legacy Mellanox OPN, retain their exact documented mapping. A family name does not confirm a port layout, GPU board version or software entitlement.
02 / ARCHITECTURE
NVIDIA's complete 10U Blackwell Ultra system with eight B300 SXM6 GPUs and ConnectX-8 fabric.
NVIDIA SXM accelerator modules. These names alone do not identify a complete server.
An eight-GPU NVL8 baseboard/platform integrated into a named NVIDIA or OEM system.
The complete named system on this page, with its own chassis, CPU, cooling, power and orderable configuration.
An unrelated Cisco blade-server model. It is not an NVIDIA B200 GPU system.
Confirm rack width/depth, rail type, service clearance, floor loading and a rated material lift.
Validate voltage, connectors, branch capacity, redundancy and sustained/peak rack power from the final BOM.
Match air or liquid cooling, CDU and facility-water requirements, hose routing and leak detection.
Validate GPU fabric, management, storage, optics, cable topology and switch-port counts separately.
Yes. This page identifies the complete named system. B200/B300 alone identifies a GPU; HGX identifies the integrated eight-GPU platform.
No. The written quotation lists the GPU generation, CPU, memory, storage, fabric, cooling, power and support.
These systems require configuration, regional power, cooling, support and delivery validation. A low generic catalog price would be misleading.
MANUFACTURER TECHNICAL VISUALS
Review the chassis, connectors and service views alongside the exact manufacturer configuration. Drawings and manufacturer visuals are not photographs of offered stock.
Model selection & order planning
NVIDIA DGX B300
Explore more products below. Please confirm compatibility before selecting a replacement.
Prepare for your office visit
Bring the full model, required configuration and delivery requirements to the office meeting.
Proof of funds and an in-person meeting are required. No brokers or intermediaries.
No futures. No preorder deposits. Email and phone price enquiries are not answered.
AI Server
P/NDGX H100
AI Server
P/NDGX B200