Hugging Face's logo

mradermacher
/
MIST-1-140B-i1-GGUF

Transformers
GGUF
English
Merge
frankenmerge
llama
llama-3.1
mist
imatrix
conversational
Model card Files
xet
 Community
mradermacher commited on
Commit
1e5a810
·
verified ·
1 Parent(s): 51f59ed

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -48,6 +48,7 @@ more details, including on how to concatenate multi-part files.
48
  | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 53.0 | lower quality |
49
  | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-IQ3_M.gguf) | i1-IQ3_M | 61.7 | |
50
  | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 66.3 | IQ3_S probably better |
 
51
  | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 82.5 | fast, recommended |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
48
  | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 53.0 | lower quality |
49
  | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-IQ3_M.gguf) | i1-IQ3_M | 61.7 | |
50
  | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 66.3 | IQ3_S probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 78.2 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/MIST-1-140B-i1-GGUF/resolve/main/MIST-1-140B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 82.5 | fast, recommended |
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant