Update README.md
Browse files
README.md
CHANGED
@@ -16,10 +16,10 @@ This repo contains GGUF format model files for [euser's wKAN-7b ](https://huggin
|
|
16 |
|
17 |
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|
18 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
19 |
-
| [wkan-7b.Q2_K.gguf ](https://huggingface.co/
|
20 |
-
| [wkan-7b.Q3_K_M.gguf ](https://huggingface.co/
|
21 |
-
| [wKAN-7b.Q4_K_S.gguf ](https://huggingface.co/
|
22 |
-
| [wkan-7b.Q4_K_M.gguf ](https://huggingface.co/
|
23 |
-
| [wkan-7b.Q5_K_M.gguf ](https://huggingface.co/
|
24 |
-
| [wkan-7b.Q6_K.gguf ](https://huggingface.co/
|
25 |
-
| [wkan-7b.Q8_0.gguf ](https://huggingface.co/
|
|
|
16 |
|
17 |
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|
18 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
19 |
+
| [wkan-7b.Q2_K.gguf ](https://huggingface.co/euser/wKAN-7b-GGUF/blob/main/wkan-7b.Q2_K.gguf ) | Q2_K | 2 | 2.72 GB| 5.22 GB | significant quality loss - not recommended for most purposes |
|
20 |
+
| [wkan-7b.Q3_K_M.gguf ](https://huggingface.co/euser/wKAN-7b-GGUF/blob/main/wkan-7b.Q3_K_M.gguf ) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
|
21 |
+
| [wKAN-7b.Q4_K_S.gguf ](https://huggingface.co/euser/wKAN-7b-GGUF/blob/main/wKAN-7b.Q4_K_S.gguf ) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
|
22 |
+
| [wkan-7b.Q4_K_M.gguf ](https://huggingface.co/euser/wKAN-7b-GGUF/blob/main/wkan-7b.Q4_K_M.gguf ) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
|
23 |
+
| [wkan-7b.Q5_K_M.gguf ](https://huggingface.co/euser/wKAN-7b-GGUF/blob/main/wkan-7b.Q5_K_M.gguf ) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
|
24 |
+
| [wkan-7b.Q6_K.gguf ](https://huggingface.co/euser/wKAN-7b-GGUF/blob/main/wkan-7b.Q6_K.gguf ) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
|
25 |
+
| [wkan-7b.Q8_0.gguf ](https://huggingface.co/euser/wKAN-7b-GGUF/blob/main/wkan-7b.Q8_0.gguf ) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
|