From ebd15b4112c52706d437ea1ae23d040090210609 Mon Sep 17 00:00:00 2001
From: "Li, Zonghang" <870644199@qq.com>
Date: Mon, 7 Apr 2025 22:12:11 +0800
Subject: [PATCH] Update README.md

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index c79e9643..a394c9d9 100644
--- a/README.md
+++ b/README.md
@@ -9,9 +9,9 @@ Worried about OOM or your device stucking? Never again! prima.cpp keeps its **me
 
 How about speed? prima.cpp is built on [llama.cpp](https://github.com/ggerganov/llama.cpp), but it’s **15x faster!** 🚀 On my poor devices, QwQ-32B generates 11 tokens per second, and Llama 3-70B generates 1.5 tokens per second. That's about the same speed as audiobook apps, from slow to fast speaking. We plan to power a **Home Siri** soon, then we can have private chats without privacy concerns.
 
-https://github.com/Lizonghang/prima.cpp/raw/main/figures/qwq%2032b.mp4
+https://github.com/user-attachments/assets/9549290e-a56f-46e1-9549-74250c1e0f7e
 
-https://github.com/Lizonghang/prima.cpp/raw/main/figures/qwq%2032b.mp4
+https://github.com/user-attachments/assets/c048f0b2-3cdf-4a3f-a5c5-a9705edfca1e
 
 And, if your devices are more powerful, you could unlock even more possibilities, like running LLM agents right in your home! If you do, we’d love to hear about it, just share your cluster setup and token throughput with us!