Hugging Face's logo

mradermacher
/
EXAONE-3.5-7.8B-Instruct-GGUF

Transformers
GGUF
English
Korean
lg-ai
exaone
exaone-3.5
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
7e7b413
•
1 Parent(s): 6b9b1fa

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -40,11 +40,15 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.3 | |
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.5 | |
 
46
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q6_K.gguf) | Q6_K | 6.5 | very good quality |
47
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q8_0.gguf) | Q8_0 | 8.4 | fast, best quality |
 
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
 
40
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.3 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.6 | fast on arm, low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.5 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.7 | |
49
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q6_K.gguf) | Q6_K | 6.5 | very good quality |
50
  | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.Q8_0.gguf) | Q8_0 | 8.4 | fast, best quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-GGUF/resolve/main/EXAONE-3.5-7.8B-Instruct.f16.gguf) | f16 | 15.7 | 16 bpw, overkill |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):