Hugging Face's logo

mradermacher
/
Midnight-Rose-70B-v2.0.3-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
589041a
·
verified ·
1 Parent(s): 01e5287

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -26,6 +26,7 @@ more details, including on how to concatenate multi-part files.
26
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-70B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-70B-v2.0.3.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
27
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-70B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-70B-v2.0.3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
28
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-70B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-70B-v2.0.3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
 
29
 
30
 
31
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
26
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-70B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-70B-v2.0.3.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
27
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-70B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-70B-v2.0.3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
28
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-70B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-70B-v2.0.3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
29
+ | [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-70B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-70B-v2.0.3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, medium quality |
30
 
31
 
32
  Here is a handy graph by ikawrakow comparing some lower-quality quant