Google TPU v3 32GB vs Google TPU v6e 32GB

The TPU v6e delivers 7.5x the BF16 throughput of the TPU v3 (918 vs 123 TFLOPS dense).

TPU v3: TPU, 2018 TPU v6e: TPU, 2024
BF16 dense lead
7.5x
TPU v6e: 918 vs 123 TFLOPS
Memory
32 vs 32 GB
Same capacity
Bandwidth
900 GB/s vs 1.6 TB/s
TPU v6e moves data faster
Download comparison sheet

Share this page

Google TPU v3 32GB vs Google TPU v6e 32GB

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

Printable version →

Google TPU v3 32GB

Full specs →

What is the Google TPU v3?

The TPU v3 is a TPU from Google on the TPU architecture, an accelerator built for AI training and inference. TPU v3 full specifications →

Can I rent the TPU v3 in the cloud?

Flopper is not tracking any live rental listings for the TPU v3 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the TPU v3 compare with other accelerators?

This page sets the TPU v3 against the TPU v6e. The TPU v3 is the older generation of the two. Both are Google parts. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the TPU v3 figures come from?

Every TPU v3 figure on this page traces to Google's own datasheet or specification table. How Flopper verifies specifications →

Google TPU v6e 32GB

Leads on BF16 Full specs →

What is the Google TPU v6e?

The TPU v6e is a TPU from Google on the TPU architecture, an accelerator built for AI training and inference. TPU v6e full specifications →

Can I rent the TPU v6e in the cloud?

Flopper is not tracking any live rental listings for the TPU v6e yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the TPU v6e compare with other accelerators?

This page sets the TPU v6e against the TPU v3. The TPU v6e is the newer generation of the two. Both are Google parts. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the TPU v6e figures come from?

Every TPU v6e figure on this page traces to Google's own datasheet or specification table. How Flopper verifies specifications →

Specifications

TPU v3
TPU v6e
Architecture
TPUTPU
Launch Year
20182024
Form Factor
——
Memory
32 GB32 GB
Memory Bandwidth
900 GB/s1.6 TB/s
TDP
——
Process Node
——

Performance (TFLOPS)

TPU v3
TPU v6e
No verified data available No verified data available
No verified data available No verified data available
No verified data available No verified data available
123 TFLOPS 918 TFLOPS
No verified data available No verified data available
No verified data available No verified data available
FP6
No verified data available No verified data available
No verified data available No verified data available
No verified data available1,836 TOPS

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 TPU v6e is the newer part: TPU (2024) against the TPU v3's TPU (2018).

Both carry 32 GB of memory. Bandwidth is 900 GB/s against 1.6 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 BF16, INT8, Sparsity and TFLOPS.

Frequently asked questions

Is the TPU v3 faster than the TPU v6e?

At BF16 precision the TPU v6e reaches 918 TFLOPS dense against 123 TFLOPS for the TPU v3. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the TPU v3 or the TPU v6e?

Choose the TPU v6e for training and high-throughput inference: it has 7.5x the BF16 throughput of the TPU v3.

Which has more memory, the TPU v3 or the TPU v6e?

Both GPUs carry 32 GB of memory. Memory bandwidth is 900 GB/s for the TPU v3 and 1.6 TB/s for the TPU v6e.

Get Comparison Updates

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

© 2026 Flopper.io - Compare the GPUs Powering AI