# Hugging Face — Run a Chatgpt-like Chatbot on a Single GPU with ROCm

- Company: Hugging Face (huggingface.co)
- Announced: 2023-05-15
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://huggingface.co/blog/chatbot-amd-gpu
- Record: https://forck.live/items/2062-run-a-chatgpt-like-chatbot-on-a-single-gpu-with-rocm
- Subject: Platform
- Models affected: Vicuna-13B, Vicuna

Running the Vicuna 13B open-source chatbot model on a single AMD GPU using ROCm, including quantization with GPTQ to reduce memory footprint.

## Evidence

Verbatim from https://huggingface.co/blog/chatbot-amd-gpu:

> In this blog, we will delve into the world of Vicuna, and explain how to run the Vicuna 13B model on a single AMD GPU with ROCm.

---

Record: https://forck.live/items/2062-run-a-chatgpt-like-chatbot-on-a-single-gpu-with-rocm
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md