Update README.md

README.md

@@ -13,21 +13,25 @@ library_name: torchao
 pipeline_tag: text-to-3d
 ---
 
-# 🚀 First INT4 Quantized Cube3D - Run on Half the VRAM
+# 🚀 First INT4 Quantized Efficient-Cube3D - Run on Half the VRAM
+![](https://img.shields.io/badge/Model_Size-1.26_GB_(82%25↓)-blueviolet)
+![](https://img.shields.io/badge/Peak_VRAM-11.3_GB_(55%25↓)-brightgreen)
+![](https://img.shields.io/badge/Setup_Time-6.9s_(97%25↓)-blue)
+![](https://img.shields.io/badge/Latency-14.2s_(on_par)-yellowgreen)
 
-![](https://img.shields.io/badge/VRAM_-11.3_GB_(55%25↓)-brightgreen)
-![](https://img.shields.io/badge/Loading-97%25_Faster-blue)
-![](https://img.shields.io/badge/Latency-Same-green)
-
-Presenting the **first INT4 quantized version** of [Cube3D v0.5](https://huggingface.co/Roblox/cube3d-v0.5), a text-to-3D mesh generative model. Quantized via **RTN W4A16** (group_size=128) using [torchao](https://github.com/pytorch/ao), it cuts peak VRAM from **25.4 GB → 11.3 GB (55%↓)** while maintaining the same inference speed and comparable shape fidelity - enabling 3D shape generation on much smaller, more accessible GPUs.
+Presenting the **first INT4 quantized efficient version** of [Cube3D v0.5](https://huggingface.co/Roblox/cube3d-v0.5), a text-to-3D mesh generative model.
+Quantized via **RTN W4A16** (group_size=128) using [torchao](https://github.com/pytorch/ao), it cuts the model size from **7.2GB → 1.3GB (82%↓)** 
+and peak VRAM from **25.4 GB → 11.3 GB (55%↓)** while maintaining the same inference speed and comparable shape fidelity - 
+enabling 3D shape generation on much smaller, more accessible GPUs.
 
 | | BF16 + Engine | BF16 + EngineFast | **INT4 + EngineFast** |
 |---|:-:|:-:|:-:|
+| 💾 Model size | 7.17 GB | 7.17 GB | **1.26 GB (82%↓)** |
 | 🎮 Peak VRAM | 21.7 GB | 25.4 GB | **11.3 GB (55%↓)** ✨ |
 | 📦 Setup time | 19.4 s | 206.9 s | **6.9 s (97%↓)** |
 | ⏱️ Latency | 90.9 s | 15.0 s | **14.2 s** |
 
-<mark>💡 The 55% VRAM reduction means this model now fits on a single 15 GB GPU (e.g. NVIDIA L4, A10, A2 etc.), bringing high-quality text-to-3D generation to individual researchers and end-user hardware.
+<mark>💡 The 82% size reduction and 55% VRAM reduction means this model now fits on a single 15 GB GPU (e.g. NVIDIA L4, A10, A2 etc.), bringing high-quality text-to-3D generation to individual researchers and end-user hardware.
 </mark>
 
 ### Original BF16 vs Quantized INT4 Comparisons: