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
conversational
Model card Files Community
2
mradermacher commited on
Commit
2bc9af9
•
1 Parent(s): 2be5764

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -32,7 +32,7 @@ more details, including on how to concatenate multi-part files.
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ1_S.gguf) | i1-IQ1_S | 7.7 | for the desperate |
35
- | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ1_M.gguf) | i1-IQ1_M | 8.5 | for the desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.8 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.9 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ2_S.gguf) | i1-IQ2_S | 11.1 | |
@@ -53,7 +53,6 @@ more details, including on how to concatenate multi-part files.
53
  | [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 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q6_K.gguf) | i1-Q6_K | 29.9 | practically like static Q6_K |
55
 
56
-
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
58
  types (lower is better):
59
 
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ1_S.gguf) | i1-IQ1_S | 7.7 | for the desperate |
35
+ | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ1_M.gguf) | i1-IQ1_M | 8.5 | mostly desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.8 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.9 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-IQ2_S.gguf) | i1-IQ2_S | 11.1 | |
 
53
  | [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 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-i1-GGUF/resolve/main/Umbra-v2.1-MoE-4x10.7.i1-Q6_K.gguf) | i1-Q6_K | 29.9 | practically like static Q6_K |
55
 
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):
58