Update README.md
Browse files
README.md
CHANGED
|
@@ -45,10 +45,11 @@ First, you need to choose your quantization, this chart is with the base of `819
|
|
| 45 |
|
| 46 |
| Quantization | VRAM Required |
|
| 47 |
|--------------|---------------|
|
| 48 |
-
|
|
| 49 |
-
|
|
| 50 |
-
|
|
| 51 |
-
|
|
|
|
|
| 52 |
|
| 53 |
**NOTE:** GPUs made before 2017 will have *significantly slower speeds* than newer GPUs, also, CPU inference will be extremely slow.
|
| 54 |
|
|
|
|
| 45 |
|
| 46 |
| Quantization | VRAM Required |
|
| 47 |
|--------------|---------------|
|
| 48 |
+
|--------------|---------------|
|
| 49 |
+
| F16 | 5 GB |
|
| 50 |
+
| Q8_0 | 3 GB+ |
|
| 51 |
+
| Q5_K_M | 2 GB+ |
|
| 52 |
+
| Q3_K_M | 1GB or CPU |
|
| 53 |
|
| 54 |
**NOTE:** GPUs made before 2017 will have *significantly slower speeds* than newer GPUs, also, CPU inference will be extremely slow.
|
| 55 |
|