NVIDIA Blackwell · Tensor Core GPU

NVIDIA B200 Tensor Core GPU

The Blackwell frontier accelerator. The B200 is a dual-die GPU with 192GB of HBM3e at 8 TB/s and fifth-generation NVLink at 1.8 TB/s, delivering roughly 2.5× the FP8 training throughput of Hopper and native FP4 for inference — the platform for the largest training clusters, built around direct liquid cooling.

  • Blackwell
  • 192GB HBM3e
  • 8 TB/s
  • DLC required

B200 specifications

Key specifications for the NVIDIA B200 Tensor Core GPU. Hard specs mirror the live catalog; confirm exact revision and configuration at quote.

NVIDIA B200 Tensor Core GPU — reference specifications
SpecificationB200
ArchitectureBlackwell (dual-die, TSMC 4NP)
GPUs per unit1 (8 per HGX B200 server)
Memory192 GB HBM3e
Memory bandwidth8 TB/s
FP8 tensor~9,000 TFLOPS (with sparsity)
FP16 / BF16 tensor~4,500 TFLOPS (with sparsity)
NVLink1.8 TB/s (5th-gen NVLink)
Board power (TDP)1000 W (up to ~1,200W DLC)
Form factorSXM6
CoolingDirect-to-chip liquid (DLC)
Typical lead time10–14 wk
Indicative priceFrom $38,500 / unit

What the B200 is for

The B200 is built for scale-out training and the most demanding inference. Two reticle-limited dies act as one GPU with 192GB of HBM3e, a second-generation Transformer Engine, and native FP4 that pushes inference throughput far beyond Hopper. That density comes with heat: the B200 is a direct-liquid-cooled part, so it belongs in a DLC-ready hall with matched CDUs and power.

Frontier-model training

Roughly 2.5× the FP8 throughput of an H100 and 1.8 TB/s NVLink make it the engine for training the largest models on huge GPU counts.

Large-scale inference (FP4)

Native FP4 and 192GB HBM3e give a step-change in tokens-per-second per rack for serving very large models cost-effectively.

Liquid-cooled greenfield

Designed for direct-to-chip liquid cooling — quote the servers, CDUs and power train together so thermals and density line up from day one.

Power & cooling for the B200

Density decides the facility. Size the electrical capacity, heat rejection and cooling method before you rack a single B200 — our free tools turn the specs above into facility numbers.

Source the B200

Add it to your quote list — free, no commitment — and we confirm a firm, itemized price, availability and lead time after review, usually within a business day.

NVIDIANVIDIA B200 Tensor Core GPU192GB HBM3e · 8TB/s · 1000W · SXM610–14 wkFrom $38,500 / unit
View full product

B200, answered

What is the NVIDIA B200?

The B200 is NVIDIA’s Blackwell-generation Tensor Core GPU — a dual-die accelerator with 192GB of HBM3e at 8 TB/s and fifth-generation NVLink at 1.8 TB/s. It roughly triples usable compute over an H100 and adds native FP4 for inference.

How much power does a B200 use and does it need liquid cooling?

The B200 draws about 1,000W air-cooled and up to ~1,200W in its highest-performance direct-liquid-cooled configuration. At these densities direct-to-chip liquid cooling is the norm — plan a DLC-ready rack, matched CDU capacity and the power to feed it.

How does the B200 compare to the H100 and H200?

The B200 is a generational jump: about 2.5× the FP8 training throughput of Hopper, 192GB HBM3e at 8 TB/s (vs 141GB/4.8 TB/s on the H200 and 80GB/3.4 TB/s on the H100), and 1.8 TB/s NVLink. The trade-off is higher power and mandatory liquid cooling.

What is the difference between the B200 and GB200?

The B200 is a discrete GPU you rack in an HGX server. The GB200 is a superchip that pairs two B200 GPUs with a Grace CPU over NVLink-C2C; 72 of those Blackwell GPUs plus 36 Grace CPUs make up a GB200 NVL72 rack — a single 72-GPU NVLink domain.

Turn the spec into a scoped quote

Our solutions engineers size compute, power and cooling together and confirm real lead times — no payment, no commitment, quotes back in about one business day.

Want a second opinion on a build?

Our engineers scope power, cooling and compute together. No payment, and quotes come back in about a business day.

Talk to an engineer