Update README.md
Browse files
README.md
CHANGED
@@ -17,10 +17,10 @@ Refer to the [original model card](https://huggingface.co/v000000/L3-8B-MegaSerp
|
|
17 |
Various GGUF format quants including FP16 and pre-generated imatrix data for v000000/L3-8B-MegaSerpentine
|
18 |
|
19 |
# List of quants in repo:
|
20 |
-
* Q8_0 imatrix
|
21 |
-
* Q6_K imatrix
|
22 |
-
* Q5_K_S imatrix
|
23 |
-
* IQ4_XS imatrix
|
24 |
|
25 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/OizoIG2tGezOo30KYXT0y.png)
|
26 |
|
|
|
17 |
Various GGUF format quants including FP16 and pre-generated imatrix data for v000000/L3-8B-MegaSerpentine
|
18 |
|
19 |
# List of quants in repo:
|
20 |
+
* Q8_0 imatrix ~8.3GB
|
21 |
+
* Q6_K imatrix ~6.4GB
|
22 |
+
* Q5_K_S imatrix ~5.4GB
|
23 |
+
* IQ4_XS imatrix ~4.3 GB
|
24 |
|
25 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/OizoIG2tGezOo30KYXT0y.png)
|
26 |
|