Update README.md

README.md

@@ -24,7 +24,7 @@ The files in this repo were then quantized to 4bit for use with [llama.cpp](http
 `gpt4-alpaca-lora-30B.GGML.q4_0.bin` | q4_0 | 4bit | 20.3GB | 23GB | Maximum compatibility |
 `gpt4-alpaca-lora-30B.GGML.q4_2.bin` | q4_2 | 4bit | 24.4GB | 28GB | Best compromise between resources, speed and quality |
 `gpt4-alpaca-lora-30B.GGML.q4_3.bin` | q4_3 | 4bit | 20.3GB | 23GB | Maximum quality 4bit, higher RAM requirements and slower inference |
-`gpt4-alpaca-lora-30B.GGML.q5_0.bin` | q5_0 | 5bit | 24.4GB | 28GB | Brand new 5bit method. Potentially higher quality than 4bit, at cost of slightly higher resources. |
+`gpt4-alpaca-lora-30B.GGML.q5_0.bin` | q5_0 | 5bit | 22.4GB | 25GB | Brand new 5bit method. Potentially higher quality than 4bit, at cost of slightly higher resources. |
 `gpt4-alpaca-lora-30B.GGML.q5_1.bin` | q5_1 | 5bit | 24.4GB | 28GB | Brand new 5bit method. Slightly higher resource usage than q5_0.|
 
 * The q4_0 file provides lower quality, but maximal compatibility. It will work with past and future versions of llama.cpp