mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ tags:
|
|
20 |
static quants of https://huggingface.co/jukofyork/creative-writer-35b-preview
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
-
weighted/imatrix quants
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -35,8 +35,15 @@ more details, including on how to concatenate multi-part files.
|
|
35 |
|:-----|:-----|--------:|:------|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q2_K.gguf) | Q2_K | 13.9 | |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q3_K_S.gguf) | Q3_K_S | 16.0 | |
|
|
|
|
|
|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q4_K_S.gguf) | Q4_K_S | 20.5 | fast, recommended |
|
|
|
|
|
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q6_K.gguf) | Q6_K | 28.8 | very good quality |
|
|
|
40 |
|
41 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
42 |
types (lower is better):
|
|
|
20 |
static quants of https://huggingface.co/jukofyork/creative-writer-35b-preview
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/creative-writer-35b-preview-i1-GGUF
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
35 |
|:-----|:-----|--------:|:------|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q2_K.gguf) | Q2_K | 13.9 | |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q3_K_S.gguf) | Q3_K_S | 16.0 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q3_K_M.gguf) | Q3_K_M | 17.7 | lower quality |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q3_K_L.gguf) | Q3_K_L | 19.2 | |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.IQ4_XS.gguf) | IQ4_XS | 19.4 | |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q4_K_S.gguf) | Q4_K_S | 20.5 | fast, recommended |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q4_K_M.gguf) | Q4_K_M | 21.6 | fast, recommended |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q5_K_S.gguf) | Q5_K_S | 24.4 | |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q5_K_M.gguf) | Q5_K_M | 25.1 | |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q6_K.gguf) | Q6_K | 28.8 | very good quality |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/creative-writer-35b-preview-GGUF/resolve/main/creative-writer-35b-preview.Q8_0.gguf) | Q8_0 | 37.3 | fast, best quality |
|
47 |
|
48 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
49 |
types (lower is better):
|