Hugging Face's logo

mradermacher
/
KONI-Llama3-8B-Instruct-20240729-GGUF

Transformers
GGUF
Korean
conversational
Model card Files Community
mradermacher commited on
Commit
d756548
·
verified ·
1 Parent(s): 7b990fa

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -32,8 +32,14 @@ more details, including on how to concatenate multi-part files.
32
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
33
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
34
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
 
 
 
 
 
35
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
36
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
 
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
39
  types (lower is better):
 
32
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
33
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
34
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
37
+ | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
40
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/KONI-Llama3-8B-Instruct-20240729-GGUF/resolve/main/KONI-Llama3-8B-Instruct-20240729.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):