Update README.md

README.md

@@ -25,22 +25,27 @@ This repository includes the quantized models for the [meow](https://huggingface
 
 ## Current models
 
-| exl2 BPW | Model Branch | Model Size |
-|-|-|-|
-| 2-Bit | main | 3.28 GB |
-| 4-Bit | 4bit | 5.61 GB |
-| 5-Bit | 5bit | 6.92 GB |
-| 6-Bit | 6bit | 8.23 GB |
-| 8-Bit | 8bit | 10.84 GB |
+| exl2 BPW | Model Branch | Model Size | Minimum VRAM (4096 Context) |
+|-|-|-|-|
+| 2-Bit | main | 3.28 GB | 6GB GPU |
+| 4-Bit | 4bit | 5.61 GB | 8GB GPU |
+| 5-Bit | 5bit | 6.92 GB | 10GB GPU, 8GB with swap |
+| 6-Bit | 6bit | 8.23 GB | 10GB GPU |
+| 8-Bit | 8bit | 10.84 GB | 12GB GPU |
+
+### Note
+
+Using a 12GB Nvidia GeForce RTX 3060 I got on average around 20 tokens per second on the 8-bit quant in full 4096 context.
 
 ## Where to use
 
 There are a couple places you can use an exl2 model, here are a few:
 
 - [oobabooga's Text Gen Webui](https://github.com/oobabooga/text-generation-webui)
+  - When using the downloader, make sure to format like this: Anthonyg5005/rishiraj-meow-10.7B-exl2**\:QuantBranch**
 - [tabbyAPI](https://github.com/theroyallab/tabbyAPI)
 - [ExUI](https://github.com/turboderp/exui)
 - [KoboldAI](https://github.com/henk717/KoboldAI) (Clone repo, don't use snapshot)
 
 # WARNING
-Model cannot be used commercially due to the Alpaca dataset license.
+Model cannot be used commercially due to the Alpaca dataset license. Only use this model for research purposes or personal use.