# Hugging Face — Google Cloud TPUs made available to Hugging Face users

- Company: Hugging Face (huggingface.co)
- Announced: 2024-07-09T00:00:00+00:00
- Category: availability-change
- Subject: Platform
- Models affected: Gemma, Llama, Mistral
- Pricing: v5litepod-1: $1.375/hour, v5litepod-4: $5.50/hour, v5litepod-8: $11.00/hour
- Source: https://huggingface.co/blog/tpu-inference-endpoints-spaces
- Record: https://forck.live/items/1859-google-cloud-tpus-made-available-to-hugging-face-users

Hugging Face announces that Google Cloud TPUs are now available on Inference Endpoints and Spaces, with three TPU v5e instance configurations and pricing per hour. Supported models include Gemma, Llama, and Mistral.

## Evidence

Verbatim from https://huggingface.co/blog/tpu-inference-endpoints-spaces:

> We're excited to share some great news! AI builders are now able to accelerate their applications with Google Cloud TPUs on Hugging Face Inference Endpoints and Spaces!

---

Record: https://forck.live/items/1859-google-cloud-tpus-made-available-to-hugging-face-users
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md