mradermacher
commited on
Commit
•
77af847
1
Parent(s):
12cf407
auto-patch README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ tags:
|
|
22 |
static quants of https://huggingface.co/Spestly/Athena-1-14B
|
23 |
|
24 |
<!-- provided-files -->
|
25 |
-
weighted/imatrix quants
|
26 |
## Usage
|
27 |
|
28 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -36,7 +36,15 @@ more details, including on how to concatenate multi-part files.
|
|
36 |
| Link | Type | Size/GB | Notes |
|
37 |
|:-----|:-----|--------:|:------|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q2_K.gguf) | Q2_K | 5.9 | |
|
|
|
|
|
|
|
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
|
|
|
|
|
|
|
|
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
|
41 |
|
42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
22 |
static quants of https://huggingface.co/Spestly/Athena-1-14B
|
23 |
|
24 |
<!-- provided-files -->
|
25 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Athena-1-14B-i1-GGUF
|
26 |
## Usage
|
27 |
|
28 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
36 |
| Link | Type | Size/GB | Notes |
|
37 |
|:-----|:-----|--------:|:------|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q2_K.gguf) | Q2_K | 5.9 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/Athena-1-14B-GGUF/resolve/main/Athena-1-14B.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
|
49 |
|
50 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|