Flopper.io Flopper.io
vs OpenAI logo

NVIDIA GB300 NVL72 GPU 288GB vs OpenAI Jalapeño

The GB300 delivers 47% more FP8 throughput than the Jalapeño (5,000 vs 3,400 TFLOPS dense). The GB300 also carries 72 GB more memory (288 GB vs 216 GB).

GB300: Blackwell Ultra, 2025 Jalapeño: Jalapeño, 2026
FP8 dense lead
+47%
GB300: 5,000 vs 3,400 TFLOPS
Memory
288 vs 216 GB
72 GB more for the GB300
Bandwidth
8.0 TB/s vs 15.4 TB/s
Jalapeño moves data faster
See rental pricing from $5.97/hr Download comparison sheet

Share this page

NVIDIA GB300 NVL72 GPU 288GB vs OpenAI Jalapeño

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

Post on X Share on LinkedIn
 Printable version →

NVIDIA GB300 NVL72 GPU 288GB

Leads on FP8 Full specs →

What is the NVIDIA GB300?

The GB300 is a GPU from NVIDIA on the Blackwell Ultra 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. GB300 full specifications →

Can I rent the GB300 in the cloud?

Yes. Cloud providers tracked by Flopper rent the GB300 by the hour, and the pricing page compares their current rates and the price history side by side. GB300 rental prices →

How does the GB300 compare with other accelerators?

This page sets the GB300 against the Jalapeño. The GB300 is the older generation of the two. This is a cross-vendor matchup, NVIDIA against OpenAI. Flopper also compares it head to head with the GB200 NVL72 GPU 186GB and H100 SXM5 80GB, across every published precision, memory and power. GB300 vs GB200 NVL72 GPU 186GB →

Where do the GB300 figures come from?

Every GB300 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

OpenAI logo

OpenAI Jalapeño

Full specs →

What is the OpenAI Jalapeño?

The Jalapeño is an ASIC from OpenAI on the Jalapeño architecture, an accelerator built for AI workloads. It has been announced but is not yet shipping. Jalapeño full specifications →

Can I rent the Jalapeño in the cloud?

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

How does the Jalapeño compare with other accelerators?

This page sets the Jalapeño against the GB300. The Jalapeño is the newer generation of the two. This is a cross-vendor matchup, OpenAI against NVIDIA. Flopper also compares it head to head with the GB200 NVL72 GPU 186GB and Maia 200, across every published precision, memory and power. Jalapeño vs GB200 NVL72 GPU 186GB →

Where do the Jalapeño figures come from?

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

Specifications

GB300
OpenAI logo
Jalapeño
Architecture
Blackwell UltraJalapeño
Launch Year
20252026
Form Factor
SXMCustom
Memory
288 GB216 GB
Memory Bandwidth
8.0 TB/s15.4 TB/s
TDP
—700 W
Process Node
4nm—

Performance (TFLOPS)

GB300
OpenAI logo
Jalapeño
1.4 TFLOPS No verified data available
83 TFLOPS No verified data available
1,250 TFLOPS
2,500 TFLOPS sparse
 No verified data available
2,500 TFLOPS
5,000 TFLOPS sparse
 No verified data available
2,500 TFLOPS
5,000 TFLOPS sparse
 No verified data available
5,000 TFLOPS
10,000 TFLOPS sparse
3,400 TFLOPS
FP6
5,000 TFLOPS
10,000 TFLOPS sparse
 No verified data available
15,000 TFLOPS
20,000 TFLOPS sparse
13,400 TFLOPS
165 TOPS
330 TOPS sparse
 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 Jalapeño is the newer part: Jalapeño (2026) against the GB300's Blackwell Ultra (2025).

The GB300 carries 72 GB more memory (288 GB against 216 GB), so larger models fit on one GPU before you shard. Bandwidth is 8.0 TB/s against 15.4 TB/s, which sets the ceiling on decode speed.

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 GB300 faster than the Jalapeño?

At FP8 precision the GB300 reaches 5,000 TFLOPS dense against 3,400 TFLOPS for the Jalapeño. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the GB300 or the Jalapeño?

Choose the GB300 for training and high-throughput inference: it has 47% more FP8 throughput than the Jalapeño. It also carries 72 GB more memory, so larger models fit on one GPU before you shard.

Which has more memory, the GB300 or the Jalapeño?

The GB300 carries 288 GB of memory versus 216 GB for the Jalapeño. Memory bandwidth is 8.0 TB/s for the GB300 and 15.4 TB/s for the Jalapeño.

How much do the GB300 and the Jalapeño cost to rent?

Live cloud listings tracked by Flopper price the GB300 from $5.97 per GPU-hour across 2 providers, and no live listings yet for the Jalapeño. The rental section on this page links to every provider, rate and the price history for each GPU.

Where to Rent

NVIDIA GB300 NVL72 GPU 288GB

Rent from

$5.97 / GPU-hr

Lowest of 3 live listings across 2 providers

See all GB300 rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

OpenAI logo

OpenAI Jalapeño

No live rental listings tracked for the Jalapeño yet.

Browse GPU cloud providers

Get Comparison Updates

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

Open in Full Compare Tool → GB300 full specs Jalapeño full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI