Hugging Face's logo

mradermacher
/
MoNeuTrix-MoE-4x7B-GGUF

Transformers
GGUF
English
Mixture of Experts
frankenmoe
Merge
mergekit
lazymergekit
CultriX/MonaTrix-v4
mlabonne/OmniTruthyBeagle-7B-v0
CultriX/MoNeuTrix-7B-v1
paulml/OmniBeagleSquaredMBX-v3-7B
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b6fa7b7
•
1 Parent(s): be36276

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -44,14 +44,13 @@ more details, including on how to concatenate multi-part files.
44
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.IQ4_XS.gguf) | IQ4_XS | 13.3 | |
45
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q4_0.gguf) | Q4_0 | 13.9 | fast, low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q4_K_S.gguf) | Q4_K_S | 14.0 | fast, recommended |
47
- | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.IQ4_NL.gguf) | IQ4_NL | 14.0 | slightly worse than Q4_K_S |
48
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q4_K_M.gguf) | Q4_K_M | 14.9 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q5_K_S.gguf) | Q5_K_S | 16.9 | |
50
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q5_K_M.gguf) | Q5_K_M | 17.4 | |
51
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q6_K.gguf) | Q6_K | 20.1 | very good quality |
52
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q8_0.gguf) | Q8_0 | 25.9 | fast, best quality |
53
 
54
-
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):
57
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.IQ4_XS.gguf) | IQ4_XS | 13.3 | |
45
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q4_0.gguf) | Q4_0 | 13.9 | fast, low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q4_K_S.gguf) | Q4_K_S | 14.0 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.IQ4_NL.gguf) | IQ4_NL | 14.0 | prefer IQ4_XS |
48
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q4_K_M.gguf) | Q4_K_M | 14.9 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q5_K_S.gguf) | Q5_K_S | 16.9 | |
50
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q5_K_M.gguf) | Q5_K_M | 17.4 | |
51
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q6_K.gguf) | Q6_K | 20.1 | very good quality |
52
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q8_0.gguf) | Q8_0 | 25.9 | fast, best quality |
53
 
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56