auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -42,7 +42,14 @@ more details, including on how to concatenate multi-part files.
|
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q2_K.gguf) | Q2_K | 4.9 | |
|
| 43 |
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q3_K_S.gguf) | Q3_K_S | 5.6 | |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality |
|
|
|
|
|
|
|
| 45 |
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 48 |
types (lower is better):
|
|
|
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q2_K.gguf) | Q2_K | 4.9 | |
|
| 43 |
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q3_K_S.gguf) | Q3_K_S | 5.6 | |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q3_K_L.gguf) | Q3_K_L | 6.7 | |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.IQ4_XS.gguf) | IQ4_XS | 6.9 | |
|
| 47 |
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q5_K_S.gguf) | Q5_K_S | 8.6 | |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q5_K_M.gguf) | Q5_K_M | 8.8 | |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q6_K.gguf) | Q6_K | 10.2 | very good quality |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/Anora-12b-GGUF/resolve/main/Anora-12b.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality |
|
| 53 |
|
| 54 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 55 |
types (lower is better):
|