Hugging Face's logo

mradermacher
/
NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF

Transformers
GGUF
English
Merge
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
f22b4f4
·
verified ·
1 Parent(s): 9b19c2f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -31,17 +31,26 @@ more details, including on how to concatenate multi-part files.
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
 
34
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ1_M.gguf) | i1-IQ1_M | 5.6 | mostly desperate |
35
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.5 | |
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ2_M.gguf) | i1-IQ2_M | 8.1 | |
37
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q2_K.gguf) | i1-Q2_K | 8.9 | IQ3_XXS probably better |
38
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
 
39
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better |
 
40
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ3_M.gguf) | i1-IQ3_M | 10.7 | |
41
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.7 | IQ3_S probably better |
 
42
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.0 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.8 | optimal size/speed/quality |
44
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.7 | fast, recommended |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q6_K.gguf) | i1-Q6_K | 19.9 | practically like static Q6_K |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ1_S.gguf) | i1-IQ1_S | 5.1 | for the desperate |
35
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ1_M.gguf) | i1-IQ1_M | 5.6 | mostly desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.5 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.2 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ2_S.gguf) | i1-IQ2_S | 7.4 | |
39
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ2_M.gguf) | i1-IQ2_M | 8.1 | |
40
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q2_K.gguf) | i1-Q2_K | 8.9 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | |
43
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better |
44
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ3_S.gguf) | i1-IQ3_S | 10.6 | beats Q3_K* |
45
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ3_M.gguf) | i1-IQ3_M | 10.7 | |
46
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.7 | IQ3_S probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.6 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.0 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q4_0.gguf) | i1-Q4_0 | 13.8 | fast, low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.8 | optimal size/speed/quality |
51
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.7 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.7 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.2 | |
54
  | [GGUF](https://huggingface.co/mradermacher/NeuralKunoichi-EroSumika-4x7B-128k-i1-GGUF/resolve/main/NeuralKunoichi-EroSumika-4x7B-128k.i1-Q6_K.gguf) | i1-Q6_K | 19.9 | practically like static Q6_K |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant