Supermicro SYS-821GE-TNHR 16NVMe+3SFF

839 503 €
693 804 €
+ 145 699 €
New
In stock
AI Server
Specification
Manufacturer
Supermicro
Form factor
8U
RAM
8192GB (DDR5 ECC REG)
GPU
8 x NVIDIA H200
Full Specs
Price
839 503 €
        
693 804 €
+ VAT 145 699 €
Add VAT
Incl shipping across EU
Add to cart
Contact manager
mail Whats App
wa [email protected]

Copy email

Copied

Supermicro SYS-821GE-TNHR 16NVMe+3SFF — Specifications

Condition
New
Manufacturer
Supermicro
Form factor
8U
RAM
8192GB (DDR5 ECC REG)
GPU
8 x NVIDIA H200
Accelerator manufacturer
NVIDIA
Accelerator model
NVIDIA H200
Installed GPU/APU count
8
Maximum GPU/APU count
8 onboard GPUs
Memory per accelerator
141GB
Total accelerator memory
1128GB
GPU memory type
HBM3e
Accelerator memory bandwidth
4800 GB/s (4.8 TB/s) per GPU
Accelerator form factor
SXM5
Accelerator interconnect
Fourth-generation NVIDIA NVLink with NVSwitch
Accelerator-to-CPU interface
PCIe 5.0 x16 per GPU
Supported compute data types
FP64, FP32, TF32, BF16, FP16, FP8, INT8
Accelerator virtualization
NVIDIA vGPU, MIG-backed vGPU and GPU passthrough
MIG support
Up to 7 isolated GPU instances per GPU
Software ecosystem
NVIDIA CUDA, CUDA-X and NGC; NVIDIA AI Enterprise-compatible
Maximum system power
9kW
Cooling
Air cooling with up to 10 heavy-duty fans and optimal fan speed control
Recommended workloads
Large-scale LLM training, fine-tuning and inference, generative AI, HPC, simulation, analytics and scientific computing
Dimensions
355.6 x 437 x 843.28 mm (H x W x D)
Weight
75.3 kg

Need a technical consultation on choosing a server?

Submit a request

Contact manager

mail Whats App
wa [email protected]

Copy email

Copied

Supermicro SYS-821GE-TNHR 16NVMe+3SFF is an 8U enterprise server storage configuration with sixteen front hot-swap 2.5-inch NVMe bays plus three front hot-swap 2.5-inch SATA bays. It is designed for AI factories, research centers, cloud providers and enterprise data centers that need fast local storage for AI, accelerated analytics and HPC workloads.

Key features:

  • Storage basket and service access: The selected storage basket comprises sixteen front hot-swap 2.5-inch NVMe bays plus three front hot-swap 2.5-inch SATA bays. Front- or rear-accessible hot-swap service, as applicable to the specified bays, helps reduce planned maintenance time without opening the main chassis.

  • Installed accelerator subsystem: The installed accelerator subsystem contains 8 x NVIDIA H200 SXM. It provides 1,128GB HBM3E (8 x 141GB). Fourth-generation NVIDIA NVLink with NVSwitch provides the high-bandwidth fabric inside the HGX H200 subsystem.

  • Storage topology and data path: The NVMe bays connect through the platform PCIe storage path. Storage, accelerator and network resources are arranged to support sustained data movement for datasets, checkpoints and local scratch space.

  • Enterprise compute platform: The compute subsystem combines dual 5th/4th Generation Intel Xeon Scalable processor platform with 8,192GB DDR5 ECC registered memory. It supplies the CPU, memory and PCIe resources required to feed the accelerator complex and host production services.

  • Management and availability: Dedicated BMC connectivity and Supermicro lifecycle-management tools, together with 6 x 3000W redundant (4+2) Titanium-level power supplies, support remote administration, component monitoring, planned service operations and resilient data-center operation.

Use cases:

  • AI model training and fine-tuning: Uses the installed NVIDIA H200 SXM subsystem for deep learning, generative AI and large-model development.

  • Inference and production AI services: Provides accelerator memory and parallel compute for LLM, multimodal and enterprise inference workloads.

  • HPC, simulation and analytics: Accelerates scientific computing, numerical simulation, engineering, analytics and other parallel workloads supported by the installed accelerator subsystem.

  • Data-intensive pipelines: Combines the specified 16NVMe+3SFF storage configuration with high-bandwidth accelerator and network paths for datasets, checkpoints, staging and local scratch storage.

Supermicro SYS-821GE-TNHR 16NVMe+3SFF is a purpose-built 8U platform for organizations that need the specified storage basket, installed NVIDIA H200 SXM acceleration and enterprise-class lifecycle management in one deployable system.

Similar products
Add VAT
AI Server
New
In stock
Gigabyte G893-ZX1-AAX2 8SFF/NVMe
Server GIGABYTE G893-ZX1-AAX2
Form factor
8U
RAM
6144GB (DDR5 ECC REG)
GPU
8 x AMD Instinct MI325X
Price
355 080 €
355 080 €
+ 74 567 € VAT
Incl shipping across EU
Add to cart
AI Server
New
In stock
Supermicro AS-8125GS-TNHR 12SFF/NVMe + 2SFF
Server Supermicro AS-8125GS-TNHR
Form factor
8U
RAM
6144GB (DDR5 ECC REG)
GPU
8 x NVIDIA H100
Price
453 360 €
453 360 €
+ 95 206 € VAT
Incl shipping across EU
Add to cart
AI Server
New
In stock
Gigabyte G893-SD1-AAX5 8SFF/NVMe
Server GIGABYTE G893-SD1-AAX5
Form factor
8U
RAM
8192GB (DDR5 ECC REG)
GPU
8 x NVIDIA B200 SXM
Price
749 618 €
749 618 €
+ 157 420 € VAT
Incl shipping across EU
Add to cart
Recently viewed
Allocate VAT
AI Server
New
In stock
Gigabyte G593-ZD1-AAX3 8SFF/NVMe
Server GIGABYTE G593-ZD1-AAX3
RAM
6144GB (DDR5 ECC REG)
GPU
8 x NVIDIA H200
Price
859 417 €
859 417 €
+ 180 478 € VAT
Incl shipping across EU
Add to cart
6 Reasons
to Buy a Server
from Servermall
1. Offer in 1 hour

Usually, it would take us 20-30 minutes. Yes, we are that quick

2. Free shipping across EU

Once again? we’ll be quick. Besides, we’ll deliver the equipment to any city.

3. 30-day moneyback

You can return any equipment within 30 days. No questions asked. Full amount refunded. No offense taken

4. Onsite diagnostics

In any warranty case, we’ll promptly repair or replace the failed equipment. Onsite. For free. For 5 years.

5. Our warehouse

We own a warehouse in Vilnius: it helps us quickly ship the equipment across Europe.

6. We stick with our clients

We’ ll always provide you with after-sales support. Our experts will help you solve any problem.

5
years
warranty
Whaaat? 5 years warranty for equipment?
Sounds crazy, right? In fact, it’s not: we are confident in the results of our diagnostics and testing. And if something goes wrong, we’ll fix it. For free.
Complete
testing

We want to make sure that our equipment is fully reliable for you. That’s why all our equipment (even new) is subject to complete diagnostics, testing, and part replacement.

Extreme
testing

We fully load our equipment with various utilities and software. Rest assured, it’ll work for a very long time.

CPU, RAM,
Power supply

The components work at full capacity and are tested for several days. If we are not sure about something, we replace it.

Full testing
of all equipment

Our regulations imply the same testing for both used and new equipment. Oh, and by the way, we complement the official manufacturer’s warranty with our own warranty.

Need an assistance? We know everything about hardware