Hugging Face's logo

mradermacher
/
Umbra-v3-MoE-4x11b-GGUF

Transformers
GGUF
English
Mixture of Experts
frankenmoe
Merge
mergekit
Himitsui/Kaiju-11B
Sao10K/Fimbulvetr-11B-v2
decapoda-research/Antares-11b-v2
beberik/Nyxene-v3-11B
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
843b527
•
1 Parent(s): 478afeb

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -37,7 +37,9 @@ more details, including on how to concatenate multi-part files.
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
39
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q2_K.gguf) | Q2_K | 13.4 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q3_K_S.gguf) | Q3_K_S | 15.8 | |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q3_K_M.gguf) | Q3_K_M | 17.5 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q3_K_L.gguf) | Q3_K_L | 19.0 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q4_K_S.gguf) | Q4_K_S | 20.8 | fast, medium quality |
 
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
39
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q2_K.gguf) | Q2_K | 13.4 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.IQ3_XS.gguf) | IQ3_XS | 14.9 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q3_K_S.gguf) | Q3_K_S | 15.8 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.IQ3_S.gguf) | IQ3_S | 15.8 | fast, beats Q3_K* |
43
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q3_K_M.gguf) | Q3_K_M | 17.5 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q3_K_L.gguf) | Q3_K_L | 19.0 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF/resolve/main/Umbra-v3-MoE-4x11b.Q4_K_S.gguf) | Q4_K_S | 20.8 | fast, medium quality |