(tpu-v5p-intro)=
# {{ product_v5p }}

{{ product_v5p }} is a training-focused generation. Each chip has {{ v5p_tensorcores }} TensorCores and {{ v5p_sparsecores }} SparseCores, and a pod holds {{ v5p_chips_per_pod }} chips connected in a {{ v5p_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_v5p }} specifications](../topics/tpu-v5p-specifications.md)**  
Per-chip and per-pod specifications for {{ product_v5p }}.
-   **[{{ product_v5p }} supported configurations](../topics/tpu-v5p-configurations.md)**  
The slice shapes you can request for {{ product_v5p }}, and how many chips and hosts each uses.
-   **[{{ product_v5p }} VM types](../topics/tpu-v5p-vm-types.md)**  
The VM types available for {{ product_v5p }} and the host resources each one provides.

:::::



:::::{container} manifest-nav

**Related information**  


[{{ product_v5p }} specifications](../topics/tpu-v5p-specifications.md)

[{{ product_v5p }} supported configurations](../topics/tpu-v5p-configurations.md)

[{{ product_v5p }} VM types](../topics/tpu-v5p-vm-types.md)

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

:::::

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

tpu-v5p-specifications
tpu-v5p-configurations
tpu-v5p-vm-types
```