Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,6 @@ language:
|
|
| 4 |
- en
|
| 5 |
base_model: google/gemma-2-2b-it
|
| 6 |
---
|
| 7 |
-
Gemma 2 2B quantized for wllama (under 2gb).
|
|
|
|
|
|
|
|
|
| 4 |
- en
|
| 5 |
base_model: google/gemma-2-2b-it
|
| 6 |
---
|
| 7 |
+
Gemma 2 2B quantized for wllama (under 2gb).
|
| 8 |
+
|
| 9 |
+
q4_0_4_8 is WAY faster when using llama.cpp, with wllama, it's about the same as q4_k.
|