diff --git a/KT-SFT/README.md b/KT-SFT/README.md
index 9237bb9e..3eb7aa41 100644
--- a/KT-SFT/README.md
+++ b/KT-SFT/README.md
@@ -284,11 +284,11 @@ chunk_size: 8192
 
 ### GPU/CPU Memory Footprint
 
-- DeepSeek-V3 (671B; 61 layers with 58 MoE): ~**70 GB** total GPU memory (multi-GPU), ~**1.2–1.3 TB** host memory.
-- DeepSeek-V2-Lite (14B; 27 layers with 26 MoE): ~**5.5 GB** GPU memory, ~**150 GB** host memory.
+- DeepSeek-V3 (671B; 61 layers with 58 MoE): ~**70 GB** total GPU VRAM (multi-GPU), ~**1.2–1.3 TB** RAM.
+- DeepSeek-V2-Lite (14B; 27 layers with 26 MoE): ~**5.5 GB** GPU VRAM, ~**30 GB** RAM.
 
 ## Conclusion
 
 By integrating **KTransformers LoRA fine-tuning** into **LLaMA-Factory**, we provide a practical guide for efficient training and deployment of MoE LLMs. KT brings cutting-edge optimizations (DeepSeek/Qwen/Kimi support with AMX-accelerated kernels), and LoRA enables customization under very low GPU memory. LLaMA-Factory offers a friendly, unified interface.
 
-This integration (akin to Unsloth-style speedups) means even models with tens to hundreds of billions of parameters can be fine-tuned and deployed with low latency on commodity hardware. You get **memory savings, speed-ups, and usability** together. We encourage you to try LLaMA-Factory + KT for your next MoE project and follow this guide. Feedback is welcome!
\ No newline at end of file
+This integration (akin to Unsloth-style speedups) means even models with tens to hundreds of billions of parameters can be fine-tuned and deployed with low latency on commodity hardware. You get **memory savings, speed-ups, and usability** together. We encourage you to try LLaMA-Factory + KT for your next MoE project and follow this guide. Feedback is welcome!