Moore Threads MTT S3000 32GB vs Moore Threads MTT S80

The MTT S3000 delivers 5% more FP32 throughput than the MTT S80 (16 vs 15 TFLOPS dense). The MTT S3000 also carries 16 GB more memory (32 GB vs 16 GB).

MTT S3000: MUSA ChunXiao, 2023 MTT S80: MUSA ChunXiao, 2024

FP32 dense lead

+5%

MTT S3000: 16 vs 15 TFLOPS

Memory

32 vs 16 GB

16 GB more for the MTT S3000

Bandwidth

448 GB/s vs 448 GB/s

Even

Download comparison sheet Printable version →

Moore Threads MTT S3000 32GB

Leads on FP32 Full specs →

What is the Moore Threads MTT S3000?

The MTT S3000 is a GPU from Moore Threads on the MUSA ChunXiao 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. MTT S3000 full specifications →

Can I rent the MTT S3000 in the cloud?

Flopper is not tracking any live rental listings for the MTT S3000 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the MTT S3000 compare with other accelerators?

This page sets the MTT S3000 against the MTT S80. The MTT S3000 is the older generation of the two. Both are Moore Threads parts, and both ship as a PCIe card, so they fit the same class of system. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the MTT S3000 figures come from?

Every MTT S3000 figure on this page traces to Moore Threads's own datasheet or specification table. How Flopper verifies specifications →

Moore Threads MTT S80

Full specs →

What is the Moore Threads MTT S80?

The MTT S80 is a GPU from Moore Threads on the MUSA ChunXiao 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. MTT S80 full specifications →

Can I rent the MTT S80 in the cloud?

Flopper is not tracking any live rental listings for the MTT S80 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the MTT S80 compare with other accelerators?

This page sets the MTT S80 against the MTT S3000. The MTT S80 is the newer generation of the two. Both are Moore Threads parts, and both ship as a PCIe card, so they fit the same class of system. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the MTT S80 figures come from?

Every MTT S80 figure on this page traces to Moore Threads's own datasheet or specification table. How Flopper verifies specifications →

Specifications

MTT S3000

MTT S80

Architecture

MUSA ChunXiaoMUSA ChunXiao

Launch Year

20232024

Form Factor

PCIePCIe

Memory

32 GB16 GB

Memory Bandwidth

448 GB/s448 GB/s

TDP

——

Process Node

——

Spec

MTT S3000

MTT S80

Architecture MUSA ChunXiaoMUSA ChunXiao

Launch Year 20232024

Form Factor PCIePCIe

Memory 32 GB16 GB

Memory Bandwidth 448 GB/s448 GB/s

TDP ——

Process Node ——

Performance (TFLOPS)

MTT S3000

MTT S80

16 TFLOPS 15 TFLOPS

FP6

Precision

MTT S3000

MTT S80

16 TFLOPS 15 TFLOPS

FP6

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 MTT S80 is the newer part: MUSA ChunXiao (2024) against the MTT S3000's MUSA ChunXiao (2023).

The MTT S3000 carries 16 GB more memory (32 GB against 16 GB), so larger models fit on one GPU before you shard. Bandwidth is 448 GB/s against 448 GB/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 FP32, Sparsity and TFLOPS.

Frequently asked questions

Is the MTT S3000 faster than the MTT S80?

At FP32 precision the MTT S3000 reaches 16 TFLOPS dense against 15 TFLOPS for the MTT S80. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the MTT S3000 or the MTT S80?

Choose the MTT S3000 for training and high-throughput inference: it has 5% more FP32 throughput than the MTT S80. It also carries 16 GB more memory, so larger models fit on one GPU before you shard.

Which has more memory, the MTT S3000 or the MTT S80?

The MTT S3000 carries 32 GB of memory versus 16 GB for the MTT S80. Memory bandwidth is 448 GB/s for the MTT S3000 and 448 GB/s for the MTT S80.

Get Comparison Updates

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

Open in Full Compare Tool → MTT S3000 full specs MTT S80 full specs Estimate cluster cost in the calculator →

Moore Threads MTT S3000 32GB vs Moore Threads MTT S80

Moore Threads MTT S3000 32GB

What is the Moore Threads MTT S3000?

Can I rent the MTT S3000 in the cloud?

How does the MTT S3000 compare with other accelerators?

Where do the MTT S3000 figures come from?

Moore Threads MTT S80

What is the Moore Threads MTT S80?

Can I rent the MTT S80 in the cloud?

How does the MTT S80 compare with other accelerators?

Where do the MTT S80 figures come from?

Specifications

Performance (TFLOPS)

FLOPS by Precision

What actually differs

Frequently asked questions

Is the MTT S3000 faster than the MTT S80?

Which should you choose, the MTT S3000 or the MTT S80?

Which has more memory, the MTT S3000 or the MTT S80?

Get Comparison Updates

Stay Updated on GPU Specs