Skip to content
State of GPU Compute 2026

Server compare

NVIDIA DGX H800 vs ASUS ESC NB8-E11

B has 800 GB more GPU memory. A costs €24.00 an hour instead of €40.00.

ANVIDIA · H100
NVIDIA DGX H800
GPU memory
80 GB × 8640 GB
System memory
32 DIMMs · 32x 64GB DDR5 4800MHz
€24.00/server·hr
Δ GPU memoryB+800 GBmore on Bmore on this side
Δ RateA−€16.00less per hour on Aless per server·hr
Δ System memoryB+6,144 GBmore on Bmore on this side
BASUS · B200
ASUS ESC NB8-E11
GPU memory
180 GB × 81,440 GB
System memory
8192GB (DDR5 ECC REG)
€40.00/server·hr
Change servers
A
B

Side by side

Every spec, line by line.

Values exactly as each builder lists them. Lines that differ are marked; identical lines are dimmed.

12 lines differ · model name and ID not counted · identical lines folded

ANVIDIA DGX H800
8× H100 · NVIDIA
BASUS ESC NB8-E11
8× B200 · ASUS
Server
Model
NVIDIA DGX H800
ASUS ESC NB8-E11
Brand(differs)
NVIDIA
ASUS
GPU(differs)
NVIDIA DELTA-NEXT Vulcan SXM5 8xNVIDIA H100 640G
8 x NVIDIA B200 SXM
GPU family(differs)
H100
B200
CPU(differs)
2x Intel Xeon Platinum 8480C (56C 105M Cache 2.00 GHz)
Configurable on request
System memory(differs)
32x 64GB DDR5 4800MHz
8192GB (DDR5 ECC REG)
Local storage(differs)
8x3.84T NVMe PCIe / 2x960Gb NVMe M.2
Configurable on request
Form factor(same on both)
Configurable on request
Configurable on request
Model ID
nvidia-dgx-h800
asus-esc-nb8-e11
GPU
Architecture(differs)
NVIDIA Hopper
NVIDIA Blackwell
Memory per GPU(differs)
80 GB HBM3
180 GB HBM3e
GPU memory per server(differs)
640 GB
1,440 GB
GPU interconnect(same on both)
NVLink, all-to-all
NVLink, all-to-all
Rental
On-demand, full server(differs)
€24.00/hr
€40.00/hr
On-demand, per GPU(differs)
€3.00/hr
€5.00/hr
Reserved, 12 months(differs)
€16.00/hr
€32.00/hr
Billing(same on both)
Per second
Per second
Rates in EUR excluding VAT. Fields a builder leaves open are configured to order.

Cost and memory

Price the run before you start.

Both panels read the live price list. A and B mark where your two servers sit.

What a run costs.

Pick a plan, how many GPUs and how long. Totals use the same hourly rates as the price list.

Plan
GPUs
Run length
ANVIDIA DGX H800
€576
8× H100 · 24 hours
BASUS ESC NB8-E11
€960
8× B200 · 24 hours

A costs €384 less for this run (40% lower).

Same run on every family
  • B300€1,152
  • B200B€960
  • H200€768
  • H100A€576
On-demand rates · EUR excl. VAT
GPU memory per server
  • B3002,304 GB
  • B200B1,440 GB
  • H2001,128 GB
  • H100A640 GB
HBM on the GPUs, not system RAM

How much fits.

GPU memory decides which models load without sharding. Compare it per card, per server, or against what you pay.

Metric
Model weights that fit, per server
ServerFP16FP8
A8× H100320B640B
B8× B200720B1,440B

Parameters, in billions, whose weights fit in GPU memory at 2 bytes (FP16) or 1 byte (FP8). KV cache and activations need room on top.

Case studies

How teams chose their server.

Write-ups from teams who picked between servers like these. Shown as a sample until approved stories exist.
Sample

Placeholder for a customer story about choosing between these two servers. Real quotes appear here once approved.

Customer nameRole, Company
Before and after · product facts
GPU memory per server
Bbefore1,440 GB
Aafter640 GB
24-hour run, on demand
Bbefore€960
Aafter€576

Sample layout: B is the server a team moved from, A the one it moved to.

Ready to pick

Rent the H100 or the B200. Switch any time.

Start on demand, keep the one that fits, and reserve it when the workload settles. Billing is per second, in euros.

On-demand ratesEUR · excl. VAT
  • B300€6.00/GPU·hr
  • B200€5.00/GPU·hr
  • H200€4.00/GPU·hr
  • H100€3.00/GPU·hr