Skip to content
State of GPU Compute 2026

Server compare

ASUS XA NB3I-E12 10NVMe vs GIGABYTE G593-ZD1-AAX3

A has 1,176 GB more GPU memory. B costs €32.00 an hour instead of €48.00.

AASUS · B300
ASUS XA NB3I-E12 10NVMe
GPU memory
288 GB × 82,304 GB
System memory
32 DIMMs · 32kh 128GB DDR5 RDIMM 6400MHz (Support up to 32 DIMM 4TB DDR5)
€48.00/server·hr
Δ GPU memoryA+1,176 GBmore on this side
Δ RateB−€16.00less per server·hr
Δ System memoryB+2,048 GBmore on this side
BGIGABYTE · H200
GIGABYTE G593-ZD1-AAX3
GPU memory
141 GB × 81,128 GB
System memory
6144GB (DDR5 ECC REG)
€32.00/server·hr

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

AASUS XA NB3I-E12 10NVMe
8× B300 · ASUS
BGIGABYTE G593-ZD1-AAX3
8× H200 · GIGABYTE
Server
Model
AASUS XA NB3I-E12 10NVMe
BGIGABYTE G593-ZD1-AAX3
Brand(differs)
AASUS
BGIGABYTE
GPU(differs)
A1 x NVIDIA HGX B300 8-GPU server
B8 x NVIDIA H200
GPU family(differs)
AB300
BH200
CPU(differs)
A2x Intel Xeon 6 6767P (64C 336M Cache 2.40 GHz)
BConfigurable on request
System memory(differs)
A32kh 128GB DDR5 RDIMM 6400MHz (Support up to 32 DIMM 4TB DDR5)
B6144GB (DDR5 ECC REG)
Local storage(differs)
A2x 1.92TB NVMe Gen5 PM9D3a
BConfigurable on request
Form factor
AConfigurable on request
BConfigurable on request
Model ID
Aasus-xa-nb3i-e12-10nvme
Bgigabyte-g593-zd1-aax3
GPU
Architecture(differs)
ANVIDIA Blackwell Ultra
BNVIDIA Hopper
Memory per GPU(differs)
A288 GB HBM3e
B141 GB HBM3e
GPU memory per server(differs)
A2,304 GB
B1,128 GB
GPU interconnect
ANVLink, all-to-all
BNVLink, all-to-all
Rental
On-demand, full server(differs)
A€48.00/hr
B€32.00/hr
On-demand, per GPU(differs)
A€6.00/hr
B€4.00/hr
Reserved, 12 months(differs)
A€40.00/hr
B€24.00/hr
Billing
APer second
BPer 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
AASUS XA NB3I-E12 10NVMe
€1,152
8× B300 · 24 hours
BGIGABYTE G593-ZD1-AAX3
€768
8× H200 · 24 hours

B costs €384 less for this run (33% lower).

Same run on every family
  • B300A€1,152
  • B200€960
  • H200B€768
  • H100€576
On-demand rates · EUR excl. VAT
GPU memory per server
  • B300A2,304 GB
  • B2001,440 GB
  • H200B1,128 GB
  • H100640 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× B3001,152B2,304B
B8× H200564B1,128B

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
Bbefore1,128 GB
Aafter2,304 GB
24-hour run, on demand
Bbefore€768
Aafter€1,152

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

Ready to pick

Rent the B300 or the H200. 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