Translation
Transformers
GGUF
English
Korean
enko
Inference Endpoints
imatrix
conversational
mradermacher commited on
Commit
fc5b585
·
verified ·
1 Parent(s): aef41fe

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -0
README.md CHANGED
@@ -37,8 +37,30 @@ more details, including on how to concatenate multi-part files.
37
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q2_K.gguf) | i1-Q2_K | 3.2 | IQ3_XXS probably better |
 
 
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
 
 
 
 
 
 
 
 
 
 
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
 
37
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate |
41
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.2 | mostly desperate |
42
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.0 | very low quality |
47
  | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q2_K.gguf) | i1-Q2_K | 3.2 | IQ3_XXS probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.3 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.5 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* |
52
  | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.0 | IQ3_S probably better |
54
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.3 | IQ3_M probably better |
55
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q4_0.gguf) | i1-Q4_0 | 4.6 | fast, low quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.6 | prefer IQ4_XS |
58
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.9 | fast, recommended |
60
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q4_1.gguf) | i1-Q4_1 | 5.1 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.7 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF/resolve/main/exaone3-instrucTrans-v2-enko-7.8b.i1-Q6_K.gguf) | i1-Q6_K | 6.5 | practically like static Q6_K |
64
 
65
  Here is a handy graph by ikawrakow comparing some lower-quality quant
66
  types (lower is better):