(tpu-v5e-intro)=
# {{ product_v5e }}

{{ product_v5e }} is a cost-efficient generation built for training and serving transformer, text-to-image and convolutional models. Each chip has {{ v5e_tensorcores }} TensorCore and a pod holds {{ v5e_chips_per_pod }} chips in a {{ v5e_topology }}.

Use the specification topic to size a slice, the configurations topic to choose a slice shape, and the VM types topic to see what each VM provides.


:::::{container} manifest-nav

-   **[{{ product_v5e }} specifications](../topics/tpu-v5e-specifications.md)**  
Per-chip and per-pod specifications for {{ product_v5e }}.
-   **[{{ product_v5e }} supported configurations](../topics/tpu-v5e-configurations.md)**  
The slice shapes you can request for {{ product_v5e }}, and how many chips and hosts each uses.
-   **[{{ product_v5e }} VM types](../topics/tpu-v5e-vm-types.md)**  
The VM types available for {{ product_v5e }} and the host resources each one provides.
% manifest:published-in unfiltered,v5e
-   **[Choose a {{ product_v5e }} slice shape](../topics/tpu-v5e-slice-planning.md)**  
Choose the slice shape for a {{ product_v5e }} TPU VM from the number of chips your workload needs, then check your quota before you create the VM.
% manifest:end

:::::



:::::{container} manifest-nav

**Related information**  


[{{ product_v5e }} specifications](../topics/tpu-v5e-specifications.md)

[{{ product_v5e }} supported configurations](../topics/tpu-v5e-configurations.md)

[{{ product_v5e }} VM types](../topics/tpu-v5e-vm-types.md)

[Create a TPU VM](../topics/tpu-create-vm.md)

:::::

```{toctree}
:maxdepth: 2
:hidden:

tpu-v5e-specifications
tpu-v5e-configurations
tpu-v5e-vm-types
tpu-v5e-slice-planning
```