Update README.md

README.md

@@ -21,7 +21,7 @@ pipeline_tag: image-text-to-text
 # Gemma3-R1984-4B
 
 # Model Overview
-Gemma3-R1984-4B is a robust Agentic AI platform built on Googls’s Gemma-3-4B model. It integrates state-of-the-art deep research via web search with multimodal file processing—including images, videos, and documents—and handles long contexts up to 8,000 tokens. Designed for local deployment on independent servers using NVIDIA L40s GPUs, it provides high security, prevents data leakage, and delivers uncensored responses.
+Gemma3-R1984-4B is a robust Agentic AI platform built on Googls’s Gemma-3-4B model. It integrates state-of-the-art deep research via web search with multimodal file processing—including images, videos, and documents—and handles long contexts up to 8,000 tokens. Designed for local deployment on independent servers using NVIDIA L40s, L4, A-100(ZeroGPU) GPUs, it provides high security, prevents data leakage, and delivers uncensored responses.
 
 # Key Features
 Multimodal Processing:
@@ -175,7 +175,7 @@ print(response.json())
 
 **Important Deployment Notice:**
 
-For optimal performance, it is highly recommended to clone the repository using the following command. This model is designed to run on a server equipped with at least an NVIDIA A100 GPU. The minimum VRAM requirement is 53GB, and VRAM usage may temporarily peak at approximately 82GB during processing.
+For optimal performance, it is highly recommended to clone the repository using the following command. This model is designed to run on a server equipped with at least an NVIDIA L40s, L4, A100(ZeroGPU) GPU. The minimum VRAM requirement is 24GB, and VRAM usage may temporarily peak at approximately 82GB during processing.
 
 ```bash
 git clone https://huggingface.co/spaces/VIDraft/Gemma-3-R1984-4B