Upload README.md

README.md

@@ -26,7 +26,7 @@ model-index:
 **The first 8-bit VibeVoice model that actually works**
 
 [![License](https://img.shields.io/badge/license-MIT-blue)](LICENSE)
-[![Model Size](https://img.shields.io/badge/size-10.8%20GB-green)](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8)
+[![Model Size](https://img.shields.io/badge/size-11.6%20GB-green)](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8)
 [![Quality](https://img.shields.io/badge/audio-identical%20quality-brightgreen)](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8)
 
 [🤗 Model](https://huggingface.co/FabioSarracino/VibeVoice-Large-Q8) • [💻 ComfyUI](https://github.com/Enemyx-net/VibeVoice-ComfyUI) • [📖 Docs](https://github.com/Enemyx-net/VibeVoice-ComfyUI/blob/main/README.md)
@@ -43,7 +43,7 @@ The secret? **Selective quantization**: I only quantized the language model (the
 
 ### Results
 - ✅ Perfect audio, identical to the original model
-- ✅ 10.8 GB instead of 17.4 GB (-38%)
+- ✅ 11.6 GB instead of 18.7 GB (-38%)
 - ✅ Uses ~12 GB VRAM instead of 20 GB
 - ✅ Works on 12 GB GPUs (RTX 3060, 4070 Ti, etc.)
 
@@ -68,11 +68,11 @@ I only quantized what can be safely quantized without losing quality.
 
 | Model | Size | Audio Quality | Status |
 |-------|------|---------------|--------|
-| Original VibeVoice | 17.4 GB | ⭐⭐⭐⭐⭐ | Full precision |
-| Other 8-bit models | 9.9 GB | 💥 NOISE | ❌ Don't work |
-| **This model** | **10.8 GB** | ⭐⭐⭐⭐⭐ | ✅ **Perfect** |
+| Original VibeVoice | 18.7 GB | ⭐⭐⭐⭐⭐ | Full precision |
+| Other 8-bit models | 10.6 GB | 💥 NOISE | ❌ Don't work |
+| **This model** | **11.6 GB** | ⭐⭐⭐⭐⭐ | ✅ **Perfect** |
 
-+0.9 GB vs other 8-bit models = perfect audio instead of noise. Worth it.
++1.0 GB vs other 8-bit models = perfect audio instead of noise. Worth it.
 
 ---
 
@@ -157,11 +157,11 @@ wavfile.write("output.wav", 24000, audio)
 - You need a production-ready model
 - You want the best size/quality balance
 
-### Use full precision (17.4 GB) if:
+### Use full precision (18.7 GB) if:
 - You have unlimited VRAM (24+ GB)
 - You're doing research requiring absolute precision
 
-### Use 4-bit NF4 (~6 GB) if:
+### Use 4-bit NF4 (~6.6 GB) if:
 - You only have 8-10 GB VRAM
 - You can accept a small quality trade-off