Flopper.io Flopper.io

NVIDIA B100 SXM 192GB vs NVIDIA GeForce RTX 5090 D V2 24GB

The GeForce RTX 5090 D V2 delivers 75% more FP32 throughput than the B100 (105 vs 60 TFLOPS dense). The B100 counters with 168 GB more memory (192 GB vs 24 GB).

B100: Blackwell, 2024 GeForce RTX 5090 D V2: Blackwell, 2025
FP32 dense lead
+75%
GeForce RTX 5090 D V2: 105 vs 60 TFLOPS
Memory
192 vs 24 GB
168 GB more for the B100
Bandwidth
8.0 TB/s vs 1.3 TB/s
B100 moves data faster
TDP
700 W vs 575 W
GeForce RTX 5090 D V2 draws 125 W less
Download comparison sheet

Share this page

NVIDIA B100 SXM 192GB vs NVIDIA GeForce RTX 5090 D V2 24GB

A post with this link shows the card on the Image tab as its preview.

Post on X Share on LinkedIn
 Printable version →

NVIDIA B100 SXM 192GB

Full specs →

What is the NVIDIA B100?

The B100 is a GPU from NVIDIA on the Blackwell architecture, an accelerator for AI training, inference and high-performance computing. It is an SXM module, the mezzanine format used in dense multi-GPU servers. B100 full specifications →

Can I rent the B100 in the cloud?

Flopper is not tracking any live rental listings for the B100 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the B100 compare with other accelerators?

This page sets the B100 against the GeForce RTX 5090 D V2. The B100 is the older generation of the two. Both are NVIDIA parts; the B100 is an SXM module while the GeForce RTX 5090 D V2 is a PCIe card. Flopper also compares it head to head with the B200 SXM 180GB, across every published precision, memory and power. B100 vs B200 SXM 180GB →

Where do the B100 figures come from?

NVIDIA published the B100 figures in marketing material rather than a datasheet, and Flopper has no independent confirmation of them. How Flopper verifies specifications →

NVIDIA GeForce RTX 5090 D V2 24GB

Leads on FP32 Full specs →

What is the NVIDIA GeForce RTX 5090 D V2?

The GeForce RTX 5090 D V2 is a GPU from NVIDIA on the Blackwell architecture, an accelerator for AI training, inference and high-performance computing. It is a PCIe add-in card, so it fits standard servers and workstations. GeForce RTX 5090 D V2 full specifications →

Can I rent the GeForce RTX 5090 D V2 in the cloud?

Flopper is not tracking any live rental listings for the GeForce RTX 5090 D V2 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the GeForce RTX 5090 D V2 compare with other accelerators?

This page sets the GeForce RTX 5090 D V2 against the B100. The GeForce RTX 5090 D V2 is the newer generation of the two. Both are NVIDIA parts; the GeForce RTX 5090 D V2 is a PCIe card while the B100 is an SXM module. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the GeForce RTX 5090 D V2 figures come from?

Every GeForce RTX 5090 D V2 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Specifications

B100
GeForce RTX 5090 D V2
Architecture
BlackwellBlackwell
Launch Year
20242025
Form Factor
SXMPCIe
Memory
192 GB24 GB
Memory Bandwidth
8.0 TB/s1.3 TB/s
TDP
700 W575 W
Process Node
4nm4nm

Performance (TFLOPS)

B100
GeForce RTX 5090 D V2
30 TFLOPS 1.6 TFLOPS
60 TFLOPS 105 TFLOPS
875 TFLOPS
sparse not published
 No verified data available
1,750 TFLOPS
sparse not published
 No verified data available
1,750 TFLOPS
sparse not published
 No verified data available
3,500 TFLOPS
sparse not published
 No verified data available
FP6
No verified data available No verified data available
7,000 TFLOPS
sparse not published
1,188 TFLOPS
2,375 TFLOPS sparse
3,500 TOPS
sparse not published
 No verified data available

Figures are dense. Where a vendor publishes a figure it sits under the dense one and never decides a winner. Hover any precision for its definition, or read the GPU glossary.

FLOPS by Precision

What actually differs

The GeForce RTX 5090 D V2 is the newer part: Blackwell (2025) against the B100's Blackwell (2024).

The B100 carries 168 GB more memory (192 GB against 24 GB), so larger models fit on one GPU before you shard. Bandwidth is 8.0 TB/s against 1.3 TB/s, which sets the ceiling on decode speed.

Power is 700 W against 575 W, and at FP32 the GeForce RTX 5090 D V2 does more work per watt. Weight the FP8 and FP16 rows for LLM work and the FP64 row for HPC.

New to the terms? The glossary explains FP64, FP32, TF32, BF16, FP16, FP8, FP4, INT8, Sparsity and TFLOPS. For how the generations relate, see NVIDIA architectures explained.

Frequently asked questions

Is the B100 faster than the GeForce RTX 5090 D V2?

At FP32 precision the GeForce RTX 5090 D V2 reaches 105 TFLOPS dense against 60 TFLOPS for the B100. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the B100 or the GeForce RTX 5090 D V2?

Choose the GeForce RTX 5090 D V2 for training and high-throughput inference: it has 75% more FP32 throughput than the B100. Choose the B100 when the model has to fit on one GPU: it carries 168 GB more memory. The GeForce RTX 5090 D V2 draws 125 W less power, which matters in an air-cooled or power-capped rack. Packaging differs too: the B100 is an SXM module while the GeForce RTX 5090 D V2 is a PCIe card, so check what your servers accept.

Which has more memory, the B100 or the GeForce RTX 5090 D V2?

The B100 carries 192 GB of memory versus 24 GB for the GeForce RTX 5090 D V2. Memory bandwidth is 8.0 TB/s for the B100 and 1.3 TB/s for the GeForce RTX 5090 D V2.

How much power do the B100 and the GeForce RTX 5090 D V2 draw?

The B100 is rated at 700 W TDP and the GeForce RTX 5090 D V2 at 575 W. On FP32 throughput per watt, the GeForce RTX 5090 D V2 is the more efficient part.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.

Open in Full Compare Tool → B100 full specs GeForce RTX 5090 D V2 full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI