Hugging Face's logo

mradermacher
/
Llama-3-Ko-Luxia-Instruct-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b9843fe
•
1 Parent(s): 0bd9b69

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -27,7 +27,9 @@ more details, including on how to concatenate multi-part files.
27
 
28
  | Link | Type | Size/GB | Notes |
29
  |:-----|:-----|--------:|:------|
 
30
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-Luxia-Instruct-GGUF/resolve/main/Llama-3-Ko-Luxia-Instruct.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality |
 
31
 
32
  Here is a handy graph by ikawrakow comparing some lower-quality quant
33
  types (lower is better):
 
27
 
28
  | Link | Type | Size/GB | Notes |
29
  |:-----|:-----|--------:|:------|
30
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-Luxia-Instruct-GGUF/resolve/main/Llama-3-Ko-Luxia-Instruct.IQ3_S.gguf) | IQ3_S | 3.9 | beats Q3_K* |
31
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-Luxia-Instruct-GGUF/resolve/main/Llama-3-Ko-Luxia-Instruct.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality |
32
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-Luxia-Instruct-GGUF/resolve/main/Llama-3-Ko-Luxia-Instruct.f16.gguf) | f16 | 16.5 | 16 bpw, overkill |
33
 
34
  Here is a handy graph by ikawrakow comparing some lower-quality quant
35
  types (lower is better):