mradermacher
/

falcon-180B-WizardLM_Orca-i1-GGUF

Transformers

GGUF

Inference Endpoints

imatrix

Model card Files Files and versions Community

mradermacher commited on Mar 7, 2024

Commit

34d63c1

verified ·

1 Parent(s): 996cae3

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -38,6 +38,8 @@ more details, including on how to concatenate multi-part files.
 | [PART 1](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 91.1 | IQ3_M probably better |
 | [PART 1](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_S.gguf.part3of3) | i1-Q4_K_S | 100.6 | almost as good as Q4_K_M |
 | [PART 1](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_M.gguf.part3of3) | i1-Q4_K_M | 107.9 | fast, medium quality |
 Here is a handy graph by ikawrakow comparing some lower-quality quant

 | [PART 1](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 91.1 | IQ3_M probably better |
 | [PART 1](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_S.gguf.part3of3) | i1-Q4_K_S | 100.6 | almost as good as Q4_K_M |
 | [PART 1](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q4_K_M.gguf.part3of3) | i1-Q4_K_M | 107.9 | fast, medium quality |
+| [PART 1](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q5_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q5_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q5_K_S.gguf.part3of3) | i1-Q5_K_S | 122.9 |  |
+| [PART 1](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-WizardLM_Orca-i1-GGUF/resolve/main/falcon-180B-WizardLM_Orca.i1-Q5_K_M.gguf.part3of3) | i1-Q5_K_M | 130.1 | best weighted quant |
 Here is a handy graph by ikawrakow comparing some lower-quality quant