Hugging Face's logo

mradermacher
/
YanoljaNEXT-Rosetta-12B-2510-i1-GGUF

Translation
Transformers
GGUF
imatrix
conversational
Model card Files
xet
 Community
mradermacher commited on
Commit
055df10
·
verified ·
1 Parent(s): 4e30412

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -71,7 +71,28 @@ more details, including on how to concatenate multi-part files.
71
  | Link | Type | Size/GB | Notes |
72
  |:-----|:-----|--------:|:------|
73
  | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
 
 
 
 
 
 
74
  | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q2_K.gguf) | i1-Q2_K | 5.2 | IQ3_XXS probably better |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
  Here is a handy graph by ikawrakow comparing some lower-quality quant
77
  types (lower is better):
 
71
  | Link | Type | Size/GB | Notes |
72
  |:-----|:-----|--------:|:------|
73
  | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
74
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ1_S.gguf) | i1-IQ1_S | 3.4 | for the desperate |
75
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ1_M.gguf) | i1-IQ1_M | 3.6 | mostly desperate |
76
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.0 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.3 | |
78
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ2_S.gguf) | i1-IQ2_S | 4.6 | |
79
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ2_M.gguf) | i1-IQ2_M | 4.8 | |
80
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.9 | very low quality |
81
  | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q2_K.gguf) | i1-Q2_K | 5.2 | IQ3_XXS probably better |
82
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.3 | lower quality |
83
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.7 | |
84
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.0 | IQ3_XS probably better |
85
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ3_M.gguf) | i1-IQ3_M | 6.2 | |
86
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.5 | IQ3_S probably better |
87
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better |
88
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.2 | |
89
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.6 | prefer IQ4_XS |
90
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q4_0.gguf) | i1-Q4_0 | 7.6 | fast, low quality |
91
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.6 | optimal size/speed/quality |
92
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
93
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.0 | |
94
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.2 | |
95
+ | [GGUF](https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-12B-2510-i1-GGUF/resolve/main/YanoljaNEXT-Rosetta-12B-2510.i1-Q6_K.gguf) | i1-Q6_K | 10.6 | practically like static Q6_K |
96
 
97
  Here is a handy graph by ikawrakow comparing some lower-quality quant
98
  types (lower is better):