Hugging Face's logo

mradermacher
/
L3.1-70B-Celeste-V0.1-BF16-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
0741720
•
1 Parent(s): 154b4fa

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -36,6 +36,8 @@ more details, including on how to concatenate multi-part files.
36
  |:-----|:-----|--------:|:------|
37
  | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-Celeste-V0.1-BF16-GGUF/resolve/main/L3.1-70B-Celeste-V0.1-BF16.Q2_K.gguf) | Q2_K | 26.5 | |
38
  | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-Celeste-V0.1-BF16-GGUF/resolve/main/L3.1-70B-Celeste-V0.1-BF16.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
 
 
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
41
  types (lower is better):
 
36
  |:-----|:-----|--------:|:------|
37
  | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-Celeste-V0.1-BF16-GGUF/resolve/main/L3.1-70B-Celeste-V0.1-BF16.Q2_K.gguf) | Q2_K | 26.5 | |
38
  | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-Celeste-V0.1-BF16-GGUF/resolve/main/L3.1-70B-Celeste-V0.1-BF16.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
39
+ | [PART 1](https://huggingface.co/mradermacher/L3.1-70B-Celeste-V0.1-BF16-GGUF/resolve/main/L3.1-70B-Celeste-V0.1-BF16.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/L3.1-70B-Celeste-V0.1-BF16-GGUF/resolve/main/L3.1-70B-Celeste-V0.1-BF16.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
40
+ | [PART 1](https://huggingface.co/mradermacher/L3.1-70B-Celeste-V0.1-BF16-GGUF/resolve/main/L3.1-70B-Celeste-V0.1-BF16.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/L3.1-70B-Celeste-V0.1-BF16-GGUF/resolve/main/L3.1-70B-Celeste-V0.1-BF16.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
43
  types (lower is better):