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
074b548
•
1 Parent(s): 3244696

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -9,7 +9,7 @@ language:
9
  - en
10
  library_name: transformers
11
  license: apache-2.0
12
- no_imatrix: "Oops: inconsistent size for (view) (4096 vs 14336)"
13
  quantized_by: mradermacher
14
  tags:
15
  - moe
@@ -40,11 +40,16 @@ more details, including on how to concatenate multi-part files.
40
  | Link | Type | Size/GB | Notes |
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q2_K.gguf) | Q2_K | 9.1 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q3_K_S.gguf) | Q3_K_S | 10.7 | |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q3_K_M.gguf) | Q3_K_M | 11.8 | lower quality |
45
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q3_K_L.gguf) | Q3_K_L | 12.8 | |
 
46
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q4_0.gguf) | Q4_0 | 13.9 | |
47
  | [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 |
 
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 | |
 
9
  - en
10
  library_name: transformers
11
  license: apache-2.0
12
+ no_imatrix: 'Oops: inconsistent size for (view) (4096 vs 14336)'
13
  quantized_by: mradermacher
14
  tags:
15
  - moe
 
40
  | Link | Type | Size/GB | Notes |
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q2_K.gguf) | Q2_K | 9.1 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.IQ3_XS.gguf) | IQ3_XS | 10.1 | |
44
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q3_K_S.gguf) | Q3_K_S | 10.7 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.IQ3_S.gguf) | IQ3_S | 10.7 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.IQ3_M.gguf) | IQ3_M | 10.9 | |
47
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q3_K_M.gguf) | Q3_K_M | 11.8 | lower quality |
48
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q3_K_L.gguf) | Q3_K_L | 12.8 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.IQ4_XS.gguf) | IQ4_XS | 13.3 | |
50
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q4_0.gguf) | Q4_0 | 13.9 | |
51
  | [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 |
52
+ | [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 |
53
  | [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 |
54
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q5_K_S.gguf) | Q5_K_S | 16.9 | |
55
  | [GGUF](https://huggingface.co/mradermacher/MoNeuTrix-MoE-4x7B-GGUF/resolve/main/MoNeuTrix-MoE-4x7B.Q5_K_M.gguf) | Q5_K_M | 17.4 | |