mradermacher
commited on
Commit
•
cfdd2f0
1
Parent(s):
8948e2e
auto-patch README.md
Browse files
README.md
CHANGED
@@ -26,17 +26,17 @@ more details, including on how to concatenate multi-part files.
|
|
26 |
|
27 |
| Link | Type | Size/GB | Notes |
|
28 |
|:-----|:-----|--------:|:------|
|
29 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-IQ1_S.gguf) | i1-IQ1_S |
|
30 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.
|
31 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.
|
32 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.
|
33 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.
|
34 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 28.
|
35 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.
|
36 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.
|
37 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.
|
38 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.
|
39 |
-
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.
|
40 |
|
41 |
|
42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
26 |
|
27 |
| Link | Type | Size/GB | Notes |
|
28 |
|:-----|:-----|--------:|:------|
|
29 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-IQ1_S.gguf) | i1-IQ1_S | 15.0 | |
|
30 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 | |
|
31 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 | |
|
32 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
|
33 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.4 | fast, lower quality |
|
34 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 28.7 | |
|
35 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.3 | IQ3_XS probably better |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | almost as good as Q4_K_M |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.1-70b-i1-GGUF/resolve/main/Samantha-1.1-70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, medium quality |
|
40 |
|
41 |
|
42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|