Update README.md

README.md

@@ -20,10 +20,10 @@ tags:
 
 DeepSeek-R1 has been making headlines for rivaling OpenAI’s O1 reasoning model while remaining fully open-source. Many users want to run it locally to ensure data privacy, reduce latency, and maintain offline access. However, fitting such a large model onto personal devices typically requires quantization (e.g. Q4_K_M), which often sacrifices accuracy (up to ~22% accuracy loss) and undermines the benefits of the local reasoning model.
 
-We’ve solved the trade-off by quantizing the DeepSeek R1 Distilled model to one-fourth its original size—without losing any accuracy. Tests on an **HP Omnibook AIPC** with an **AMD Ryzen™ AI 9 HX 370 processor** showed a decoding speed of **66.40 tokens per second** and a peak RAM usage of just **1228 MB** in NexaQuant version—compared to only **25.28 tokens** per second and **3788 MB RAM** in the unquantized version—while NexaQuant **maintaining full precision model accuracy.**
+We’ve solved the trade-off by quantizing the DeepSeek R1 Distilled model to 1/4 its original size—without losing any accuracy. Tests on an **HP Omnibook AIPC** with an **AMD Ryzen™ AI 9 HX 370 processor** showed a decoding speed of **66.40 tokens per second** and a peak RAM usage of just **1228 MB** in NexaQuant version—compared to only **25.28 tokens** per second and **3788 MB RAM** in the unquantized version—while NexaQuant **maintaining full precision model accuracy.**
 
 
-## NexaQunat Use Case Example
+## NexaQunat Use Case Demo
 
 Here’s a comparison of how a standard Q4_K_M and NexaQuant-4Bit handle a common investment banking brain teaser question. NexaQuant excels in accuracy while shrinking the model file size by 4 times.
 
@@ -40,7 +40,7 @@ Right Answer: 47
 
 ## Benchmarks
 
-NexaQuant on Reasoning Benchmarks Compared to BF16 and LMStudio's Q4_K_M
+The benchmarks show that NexaQuant’s 4-bit model preserves the reasoning capacity of the original 16-bit model, delivering uncompromised performance in a significantly smaller memory & storage footprint.
 
 **Reasoning Capacity:**
 
@@ -65,7 +65,7 @@ NexaQuant on Reasoning Benchmarks Compared to BF16 and LMStudio's Q4_K_M
 | **IFEval - Prom - Loose**  | 13.86      | 10.29             | 15.71             |
 | **IFEval - Prom - Strict** | 12.57      | 8.09              | 15.16             |
 
-## How to run locally
+## Run locally
 
 NexaQuant is compatible with **Nexa-SDK**, **Ollama**, **LM Studio**, **Llama.cpp**, and any llama.cpp based project. Below, we outline multiple ways to run the model locally.
 
@@ -112,7 +112,7 @@ Get the latest version from the [official website](https://lmstudio.ai/).
 
 ## What's next
 
-1. This model is built for complex problem-solving, which is why it sometimes takes a long thinking process even for simple questions. We recognize this and are working on improving it in the next update.
+1. This model is built for complex problem-solving, which is why it sometimes takes a long thinking process even for simple questions. We recognized this and are working on improving it in the next update.
 
 2. Inference Nexa Quantized Deepseek-R1 distilled model on NPU.
 
@@ -123,3 +123,5 @@ If you liked our work, feel free to ⭐Star [Nexa's GitHub Repo](https://github.
 Interested in running DeepSeek R1 on your own devices with optimized CPU, GPU, and NPU acceleration or compressing your finetuned DeepSeek-Distill-R1? [Let’s chat!](https://nexa.ai/book-a-call)
 
 [Blogs](https://nexa.ai/blogs/deepseek-r1-nexaquant) | [Discord](https://discord.gg/nexa-ai) | [X(Twitter)](https://x.com/nexa_ai)
+
+Join Discord server for help and discussion.