Hugging Face's logo

mradermacher
/
KoDolph-2x8b-Instruct-GGUF

Transformers
GGUF
PyTorch
English
Korean
mergekit
Merge
facebook
meta
llama
llama-3
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
741153a
·
verified ·
1 Parent(s): 31798db

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -201,9 +201,11 @@ more details, including on how to concatenate multi-part files.
201
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
202
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
203
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
 
204
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
205
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
206
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
 
207
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
208
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
209
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
 
201
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
202
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
203
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
204
+ | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
205
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
206
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
207
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
208
+ | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
209
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
210
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
211
  | [GGUF](https://huggingface.co/mradermacher/KoDolph-2x8b-Instruct-GGUF/resolve/main/KoDolph-2x8b-Instruct.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |