Skip to content

NVIDIA · Blackwell · 2024

NVIDIA B200. 180 GB HBM3e, 2250 TFLOPS FP16 tensor.

Frontier-model training and large-batch inference on Blackwell, with 180 GB of HBM3e per GPU.

B200 on demand

from$10.01/hr per GPU
Availability
Available now · 1 region
Billing
By the second on most GPUs, a few by the minute
8+ GPUs or a month
Launch any size yourself, or prepay a machine for 1 to 12 months at a discount. Custom quotes on request.

The card

180 GB of HBM3e. At 8.0 TB/s.

Memory
180 GB
HBM3e
Bandwidth
8.0 TB/s
Memory to compute
FP16 tensor
2250
TFLOPS
Per node
8 GPUs
NVLink, 1000 W each

Workloads

What teams run on the B200. Each one opens the launch form, sized.

Full specs

NVIDIA B200 specifications.

Memory

Memory
180 GB
Type
HBM3e
Bandwidth
8.0 TB/s

Compute

FP32
75 TFLOPS
FP16 tensor
2250 TFLOPS
INT8
4500 TOPS

Power and form

TDP
1000 W
Form factor
SXM
Architecture
Blackwell
Released
2024

Node

GPUs per node
8
Interconnect
NVLink
Maker
NVIDIA

Alternatives

Alternatives to the B200. Same account, different price and performance.

GPUMemory · FP16 tensorStands outPrice gapFrom
NVIDIA B200This GPU180 GB HBM3e · 2250 TFLOPS$10.01/hr
NVIDIA B300288 GB HBM3e · 2250 TFLOPS+108 GB memory+70%$17.02/hr
NVIDIA GB200186 GB HBM3e · 2500 TFLOPSNot in stock right now
NVIDIA GB300288 GB HBM3e · 2500 TFLOPS+108 GB memoryIn stock · $14.30/GPU-hr3-month term, prepaid in full
AMD MI300X192 GB HBM3 · 1307.4 TFLOPS-42% FP16 tensor-52%$4.85/hr

Questions

Renting the B200. What buyers ask first.

Other GPUs

Browse every GPU by architecture.