Hugging Face's logo

mradermacher
/
UNAversal-8x7B-v1beta-i1-GGUF

Transformers
GGUF
English
UNA
juanako
mixtral
MoE
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
a1205c6
•
1 Parent(s): 20f16d0

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -36,9 +36,13 @@ more details, including on how to concatenate multi-part files.
36
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.5 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.7 | IQ3_XS probably better |
38
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
 
39
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.3 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
41
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | practically like static Q6_K |
43
 
44
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.5 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.7 | IQ3_XS probably better |
38
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
39
+ | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.3 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q4_0.gguf) | i1-Q4_0 | 26.8 | fast, low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
43
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.5 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 | |
46
  | [GGUF](https://huggingface.co/mradermacher/UNAversal-8x7B-v1beta-i1-GGUF/resolve/main/UNAversal-8x7B-v1beta.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | practically like static Q6_K |
47
 
48