Commit
•
e4a8067
1
Parent(s):
2433602
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -38,7 +38,7 @@ more details, including on how to concatenate multi-part files.
|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q3_K_L.gguf) | Q3_K_L | 24.4 | |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.IQ4_XS.gguf) | IQ4_XS | 25.6 | |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q4_0.gguf) | Q4_0 | 26.7 | fast, low quality |
|
| 41 |
-
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.IQ4_NL.gguf) | IQ4_NL | 27.0 |
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q4_K_S.gguf) | Q4_K_S | 27.0 | fast, recommended |
|
| 43 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q4_K_M.gguf) | Q4_K_M | 28.7 | fast, recommended |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q5_K_S.gguf) | Q5_K_S | 32.5 | |
|
|
@@ -46,7 +46,6 @@ more details, including on how to concatenate multi-part files.
|
|
| 46 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q6_K.gguf) | Q6_K | 38.6 | very good quality |
|
| 47 |
| [PART 1](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q8_0.gguf.part2of2) | Q8_0 | 49.8 | fast, best quality |
|
| 48 |
|
| 49 |
-
|
| 50 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 51 |
types (lower is better):
|
| 52 |
|
|
|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q3_K_L.gguf) | Q3_K_L | 24.4 | |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.IQ4_XS.gguf) | IQ4_XS | 25.6 | |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q4_0.gguf) | Q4_0 | 26.7 | fast, low quality |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.IQ4_NL.gguf) | IQ4_NL | 27.0 | prefer IQ4_XS |
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q4_K_S.gguf) | Q4_K_S | 27.0 | fast, recommended |
|
| 43 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q4_K_M.gguf) | Q4_K_M | 28.7 | fast, recommended |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q5_K_S.gguf) | Q5_K_S | 32.5 | |
|
|
|
|
| 46 |
| [GGUF](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q6_K.gguf) | Q6_K | 38.6 | very good quality |
|
| 47 |
| [PART 1](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-GGUF/resolve/main/NoromaidxOpenGPT4-2.Q8_0.gguf.part2of2) | Q8_0 | 49.8 | fast, best quality |
|
| 48 |
|
|
|
|
| 49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 50 |
types (lower is better):
|
| 51 |
|