diff --git a/README.md b/README.md
index fce18a7f..5673b0af 100644
--- a/README.md
+++ b/README.md
@@ -99,7 +99,7 @@ Implementation of paper:
 - From the perspective of model size and input image ratio, we have built a series of models on the mobile terminal to facilitate flexible applications in different scenarios. 
 - All checkpoints are trained with 400 epochs without distillation.
 - Results of the mAP and speed are evaluated on [COCO val2017](https://cocodataset.org/#download) dataset, and the input resolution is the Size in the table.
-- Speed is tested with MNN 2.3.0 AArch64. During the speed test, the arm82 acceleration is turned on, the inference warm-up is performed 10 times, and the cycle is performed 100 times.
+- Speed is tested on MNN 2.3.0 AArch64 with 2 threads by arm82 acceleration. The inference warm-up is performed 10 times, and the cycle is performed 100 times.
 - Qualcomm 888(sm8350), Dimensity 720(mt6853) and Qualcomm 660(sdm660) correspond to chips with different performances at the high, middle and low end respectively, which can be used as a reference for model capabilities under different chips.
 - Refer to [Test NCNN Speed](./docs/Test_NCNN_speed.md) tutorial to reproduce the NCNN speed results of YOLOv6Lite.
 
diff --git a/README_cn.md b/README_cn.md
index 286b476c..9c225235 100644
--- a/README_cn.md
+++ b/README_cn.md
@@ -93,7 +93,7 @@
 - 从模型尺寸和输入图片比例两种角度，在构建了移动端系列模型，方便不同场景下的灵活应用。
 - 所有权重都经过 400 个 epoch 的训练，并且没有使用蒸馏技术。
 -  mAP 和速度指标是在 COCO val2017 数据集上评估的，输入分辨率为表格中对应展示的。
-- 使用 MNN 2.3.0 AArch64 进行速度测试。测速时，开启arm82加速，推理预热10次，循环100次。
+- 使用 MNN 2.3.0 AArch64 进行速度测试。测速时，采用2个线程，并开启arm82加速，推理预热10次，循环100次。
 - 高通888(sm8350)、天玑720(mt6853)和高通660(sdm660)分别对应高中低端不同性能的芯片，可以作为不同芯片下机型能力的参考。
 - [NCNN 速度测试](./docs/Test_NCNN_speed.md)教程可以帮助展示及复现 YOLOv6Lite 的 NCNN 速度结果。
 
diff --git a/configs/yolov6_lite/README.md b/configs/yolov6_lite/README.md
index 8127e908..6cff03fb 100644
--- a/configs/yolov6_lite/README.md
+++ b/configs/yolov6_lite/README.md
@@ -17,6 +17,6 @@ English | [简体中文](./README_cn.md)
 - From the perspective of model size and input image ratio, we have built a series of models on the mobile terminal to facilitate flexible applications in different scenarios. 
 - All checkpoints are trained with 400 epochs without distillation.
 - Results of the mAP and speed are evaluated on [COCO val2017](https://cocodataset.org/#download) dataset, and the input resolution is the Size in the table.
-- Speed is tested with MNN 2.3.0 AArch64. During the speed test, the arm82 acceleration is turned on, the inference warm-up is performed 10 times, and the cycle is performed 100 times.
+- Speed is tested on MNN 2.3.0 AArch64 with 2 threads by arm82 acceleration. The inference warm-up is performed 10 times, and the cycle is performed 100 times.
 - Qualcomm 888(sm8350), Dimensity 720(mt6853) and Qualcomm 660(sdm660) correspond to chips with different performances at the high, middle and low end respectively, which can be used as a reference for model capabilities under different chips.
 - Refer to [Test NCNN Speed](./docs/Test_NCNN_speed.md) tutorial to reproduce the NCNN speed results of YOLOv6Lite.
\ No newline at end of file
diff --git a/configs/yolov6_lite/README_cn.md b/configs/yolov6_lite/README_cn.md
index a1b60502..eb9651e5 100644
--- a/configs/yolov6_lite/README_cn.md
+++ b/configs/yolov6_lite/README_cn.md
@@ -18,6 +18,6 @@
 - 从模型尺寸和输入图片比例两种角度，在构建了移动端系列模型，方便不同场景下的灵活应用。
 - 所有权重都经过 400 个 epoch 的训练，并且没有使用蒸馏技术。
 -  mAP 和速度指标是在 COCO val2017 数据集上评估的，输入分辨率为表格中对应展示的。
-- 使用 MNN 2.3.0 AArch64 进行速度测试。测速时，开启arm82加速，推理预热10次，循环100次。
+- 使用 MNN 2.3.0 AArch64 进行速度测试。测速时，采用2个线程，并开启arm82加速，推理预热10次，循环100次。
 - 高通888(sm8350)、天玑720(mt6853)和高通660(sdm660)分别对应高中低端不同性能的芯片，可以作为不同芯片下机型能力的参考。
 - [NCNN 速度测试](./docs/Test_NCNN_speed.md)教程可以帮助展示及复现 YOLOv6Lite 的 NCNN 速度结果。
\ No newline at end of file