From a3d5d53605207785908fb952779400bb11036073 Mon Sep 17 00:00:00 2001
From: Jiaqi Liao <30439460+SkqLiao@users.noreply.github.com>
Date: Fri, 13 Feb 2026 22:35:36 +0800
Subject: [PATCH] Update MiniMax-M2.5.md (#1849)

---
 doc/en/MiniMax-M2.5.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/doc/en/MiniMax-M2.5.md b/doc/en/MiniMax-M2.5.md
index 049a9c3..c378f8d 100644
--- a/doc/en/MiniMax-M2.5.md
+++ b/doc/en/MiniMax-M2.5.md
@@ -14,7 +14,7 @@ This tutorial demonstrates how to run MiniMax-M2.5 model inference using SGLang
 
 **Minimum Configuration:**
 - **GPU**: NVIDIA RTX 2x4090 48GB (or equivalent with at least total 48GB VRAM available)
-- **CPU**: x86 CPU with AVX512F support (e.g., Intel Sapphire Rapids)
+- **CPU**: x86 CPU with AVX512BF16 support (e.g., Intel Sapphire Rapids)
 - **RAM**: At least 200GB system memory
 - **Storage**: ~200GB for model weights (FP8 weight, same weight folder for CPU and GPU)