readme: add quants update
Browse files
README.md
CHANGED
|
@@ -77,9 +77,10 @@ quantize \
|
|
| 77 |
# Quants:
|
| 78 |
```
|
| 79 |
- bf16 [size: 439gb]
|
| 80 |
-
- q8_0 (
|
| 81 |
- q4_k_m [size: 132gb]
|
| 82 |
-
- q2_k
|
|
|
|
| 83 |
- q3_k_s (generating, using importance matrix) [estimated size: 96.05gb]
|
| 84 |
```
|
| 85 |
|
|
@@ -91,7 +92,6 @@ quantize \
|
|
| 91 |
- q6_k
|
| 92 |
- iq4_nl
|
| 93 |
- iq4_xs
|
| 94 |
-
- iq2_xxs
|
| 95 |
- iq2_xs
|
| 96 |
- iq2_s
|
| 97 |
- iq2_m
|
|
|
|
| 77 |
# Quants:
|
| 78 |
```
|
| 79 |
- bf16 [size: 439gb]
|
| 80 |
+
- q8_0 (later, please use q4_k_m for now) [estimated size: 233.27gb]
|
| 81 |
- q4_k_m [size: 132gb]
|
| 82 |
+
- q2_k [size: 80gb]
|
| 83 |
+
- iq2_xxs (generating, using importance matrix)
|
| 84 |
- q3_k_s (generating, using importance matrix) [estimated size: 96.05gb]
|
| 85 |
```
|
| 86 |
|
|
|
|
| 92 |
- q6_k
|
| 93 |
- iq4_nl
|
| 94 |
- iq4_xs
|
|
|
|
| 95 |
- iq2_xs
|
| 96 |
- iq2_s
|
| 97 |
- iq2_m
|