Hugging Face's logo

mradermacher
/
WizardLM-2-8x22B-GGUF

Transformers
English
Inference Endpoints
Model card Files Community
2
mradermacher commited on
Commit
1de3aa7
•
1 Parent(s): 81f6925

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -43,7 +43,6 @@ more details, including on how to concatenate multi-part files.
43
  | [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q6_K.gguf.part3of3) | Q6_K | 115.6 | very good quality |
44
  | [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q8_0.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q8_0.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q8_0.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q8_0.gguf.part4of4) | Q8_0 | 149.5 | fast, best quality |
45
 
46
-
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
49
 
 
43
  | [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q6_K.gguf.part3of3) | Q6_K | 115.6 | very good quality |
44
  | [PART 1](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q8_0.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q8_0.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q8_0.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/WizardLM-2-8x22B-GGUF/resolve/main/WizardLM-2-8x22B.Q8_0.gguf.part4of4) | Q8_0 | 149.5 | fast, best quality |
45
 
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
48