NVIDIA GH200 144GB HBM3e vs Rebellions Rebel100

The Rebel100 delivers 3% more FP8 throughput than the GH200 (2,048 vs 1,979 TFLOPS dense).

GH200: Hopper, 2024

FP8 dense lead

+3%

Rebel100: 2,048 vs 1,979 TFLOPS

Memory

144 vs 144 GB

Same capacity

Bandwidth

4.9 TB/s vs 4.8 TB/s

GH200 moves data faster

TDP

1.0 kW vs 600 W

Rebel100 draws 400 W less

Download comparison sheet Printable version →

NVIDIA GH200 144GB HBM3e

Full specs →

What is the NVIDIA GH200?

The GH200 is a GPU from NVIDIA on the Hopper architecture, an accelerator for AI training, inference and high-performance computing. It is a superchip that pairs a CPU and accelerators on one board for rack-scale systems. GH200 full specifications →

Can I rent the GH200 in the cloud?

Flopper is not tracking any live rental listings for the GH200 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the GH200 compare with other accelerators?

This page sets the GH200 against the Rebel100. This is a cross-vendor matchup, NVIDIA against Rebellions. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the GH200 figures come from?

Every GH200 figure on this page traces to NVIDIA's own datasheet or specification table. How Flopper verifies specifications →

Rebellions Rebel100

Leads on FP8 Full specs →

What is the Rebellions Rebel100?

The Rebel100 is an ASIC from Rebellions on the REBEL architecture, an accelerator built for AI workloads. It has been announced but is not yet shipping. Rebel100 full specifications →

Can I rent the Rebel100 in the cloud?

Flopper is not tracking any live rental listings for the Rebel100 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the Rebel100 compare with other accelerators?

This page sets the Rebel100 against the GH200. This is a cross-vendor matchup, Rebellions against NVIDIA. Flopper also compares it head to head with the ATOM-Max, across every published precision, memory and power. Rebel100 vs ATOM-Max →

Where do the Rebel100 figures come from?

Every Rebel100 figure on this page traces to Rebellions's own datasheet or specification table. How Flopper verifies specifications →

Specifications

GH200

Rebel100

Architecture

HopperREBEL

Launch Year

2024—

Form Factor

Superchip—

Memory

144 GB144 GB

Memory Bandwidth

4.9 TB/s4.8 TB/s

TDP

1.0 kW600 W

Process Node

4nm4nm

Spec

GH200

Rebel100

Architecture HopperREBEL

Launch Year 2024—

Form Factor Superchip—

Memory 144 GB144 GB

Memory Bandwidth 4.9 TB/s4.8 TB/s

TDP 1.0 kW600 W

Process Node 4nm4nm

Performance (TFLOPS)

GH200

Rebel100

34 TFLOPS

67 TFLOPS

494 TFLOPS

989 TFLOPS sparse

990 TFLOPS

1,979 TFLOPS sparse

990 TFLOPS

1,979 TFLOPS sparse

1,024 TFLOPS

1,979 TFLOPS

3,958 TFLOPS sparse

2,048 TFLOPS

FP6

1,979 TOPS

3,958 TOPS sparse

Tensor Core

67 TFLOPS

Precision

GH200

Rebel100

34 TFLOPS

67 TFLOPS

494 TFLOPS

989 TFLOPS sparse

990 TFLOPS

1,979 TFLOPS sparse

990 TFLOPS

1,979 TFLOPS sparse

1,024 TFLOPS

1,979 TFLOPS

3,958 TFLOPS sparse

2,048 TFLOPS

FP6

1,979 TOPS

3,958 TOPS sparse

Tensor Core

67 TFLOPS

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

Both carry 144 GB of memory. Bandwidth is 4.9 TB/s against 4.8 TB/s, which sets the ceiling on decode speed.

Power is 1.0 kW against 600 W, and at FP32 the GH200 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, INT8, Sparsity and TFLOPS. For how the generations relate, see NVIDIA architectures explained.

Frequently asked questions

Is the GH200 faster than the Rebel100?

At FP8 precision the Rebel100 reaches 2,048 TFLOPS dense against 1,979 TFLOPS for the GH200. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the GH200 or the Rebel100?

Choose the Rebel100 for training and high-throughput inference: it has 3% more FP8 throughput than the GH200. The Rebel100 draws 400 W less power, which matters in an air-cooled or power-capped rack.

Which has more memory, the GH200 or the Rebel100?

Both GPUs carry 144 GB of memory. Memory bandwidth is 4.9 TB/s for the GH200 and 4.8 TB/s for the Rebel100.

How much power do the GH200 and the Rebel100 draw?

The GH200 is rated at 1.0 kW TDP and the Rebel100 at 600 W. On FP32 throughput per watt, the GH200 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 → GH200 full specs Rebel100 full specs Estimate cluster cost in the calculator →

NVIDIA GH200 144GB HBM3e vs Rebellions Rebel100

NVIDIA GH200 144GB HBM3e

What is the NVIDIA GH200?

Can I rent the GH200 in the cloud?

How does the GH200 compare with other accelerators?

Where do the GH200 figures come from?

Rebellions Rebel100

What is the Rebellions Rebel100?

Can I rent the Rebel100 in the cloud?

How does the Rebel100 compare with other accelerators?

Where do the Rebel100 figures come from?

Specifications

Performance (TFLOPS)

FLOPS by Precision

What actually differs

Frequently asked questions

Is the GH200 faster than the Rebel100?

Which should you choose, the GH200 or the Rebel100?

Which has more memory, the GH200 or the Rebel100?

How much power do the GH200 and the Rebel100 draw?

Related comparisons

Get Comparison Updates

Stay Updated on GPU Specs