Hugging Face's logo

mradermacher
/
Umbra-v2.1-MoE-4x10.7-i1-GGUF

Transformers
GGUF
English
Mixture of Experts
Merge
mergekit
Solar Moe
Solar
Umbra
Inference Endpoints
Model card Files Community
2
mradermacher commited on
Commit
d6b22ce
•
1 Parent(s): f68f768

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -43,10 +43,10 @@ more details, including on how to concatenate multi-part files.
43
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ3_M.gguf) | i1-IQ3_M | 16.1 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.5 | IQ3_S probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q3_K_L.gguf) | i1-Q3_K_L | 19.0 | IQ3_M probably better |
46
- | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.8 | almost as good as Q4_K_M |
47
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q4_K_M.gguf) | i1-Q4_K_M | 22.1 | fast, medium quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q5_K_S.gguf) | i1-Q5_K_S | 25.1 | |
49
- | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.9 | best weighted quant |
50
 
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
43
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ3_M.gguf) | i1-IQ3_M | 16.1 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.5 | IQ3_S probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q3_K_L.gguf) | i1-Q3_K_L | 19.0 | IQ3_M probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.8 | optimal size/speed/quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q4_K_M.gguf) | i1-Q4_K_M | 22.1 | fast, medium quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q5_K_S.gguf) | i1-Q5_K_S | 25.1 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.9 | |
50
 
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant