From cbf7fc7e2f7de4400dd848ff2c221a6c8ea0384f Mon Sep 17 00:00:00 2001
From: Kawrakow <iwankawrakow@gmail.com>
Date: Sun, 22 Feb 2026 07:42:17 +0100
Subject: [PATCH] Update README with warning about '_XL' models from Unsloth

Added important note regarding quantized models from Unsloth.
---
 README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/README.md b/README.md
index c76cc39c..ea98f291 100644
--- a/README.md
+++ b/README.md
@@ -6,6 +6,9 @@
 
 This repository is a fork of [llama.cpp](https://github.com/ggerganov/llama.cpp) with better CPU and hybrid GPU/CPU performance, new SOTA quantization types, first-class Bitnet support, better DeepSeek performance via MLA, FlashMLA, fused MoE operations and tensor overrides for hybrid GPU/CPU inference, row-interleaved quant packing, etc.
 
+>[!IMPORTANT]
+>Do not use quantized models from Unsloth that have `_XL` in their name. These are likely to not work with `ik_llama.cpp`.
+  
 ## Quickstart
 
 ### Prerequisites