TheBloke commited on
Commit
88f87e2
1 Parent(s): 86378ce

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -22,8 +22,8 @@ The files in this repo were then quantized to 4bit for use with [llama.cpp](http
22
  | Name | Quant method | Bits | Size | RAM required | Use case |
23
  | ---- | ---- | ---- | ---- | ---- | ----- |
24
  `gpt4-alpaca-lora-30B.GGML.q4_0.bin` | q4_0 | 4bit | 20.3GB | 23GB | Maximum compatibility |
25
- `gpt4-alpaca-lora-30B.GGML.q4_2.bin` | q4_2 | 4bit | 24.4GB | 28GB | Best compromise between resources, speed and quality |
26
- `gpt4-alpaca-lora-30B.GGML.q4_3.bin` | q4_3 | 4bit | 20.3GB | 23GB | Maximum quality 4bit, higher RAM requirements and slower inference |
27
  `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. |
28
  `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.|
29
 
 
22
  | Name | Quant method | Bits | Size | RAM required | Use case |
23
  | ---- | ---- | ---- | ---- | ---- | ----- |
24
  `gpt4-alpaca-lora-30B.GGML.q4_0.bin` | q4_0 | 4bit | 20.3GB | 23GB | Maximum compatibility |
25
+ `gpt4-alpaca-lora-30B.GGML.q4_2.bin` | q4_2 | 4bit | 20.3GB | 23GB | Best compromise between resources, speed and quality |
26
+ `gpt4-alpaca-lora-30B.GGML.q4_3.bin` | q4_3 | 4bit | 24.4GB | 28GB | Maximum quality 4bit, higher RAM requirements and slower inference |
27
  `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. |
28
  `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.|
29