auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -45,10 +45,16 @@ more details, including on how to concatenate multi-part files.
|
|
| 45 |
| Link | Type | Size/GB | Notes |
|
| 46 |
|:-----|:-----|--------:|:------|
|
| 47 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
|
|
|
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality |
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better |
|
|
|
|
|
|
|
| 50 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | |
|
|
|
|
| 51 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality |
|
|
|
|
|
|
|
| 52 |
|
| 53 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 54 |
types (lower is better):
|
|
|
|
| 45 |
| Link | Type | Size/GB | Notes |
|
| 46 |
|:-----|:-----|--------:|:------|
|
| 47 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | |
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality |
|
| 50 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality |
|
| 53 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | |
|
| 54 |
+
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better |
|
| 55 |
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality |
|
| 56 |
+
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended |
|
| 57 |
+
| [GGUF](https://huggingface.co/mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF/resolve/main/Huihui-gpt-oss-20b-BF16-abliterated-v2.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | practically like static Q6_K |
|
| 58 |
|
| 59 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 60 |
types (lower is better):
|