Hugging Face's logo

mradermacher
/
Vakeel-8B-v2-mini-GGUF

Transformers
GGUF
English
unsloth
trl
sft
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
537ad07
•
1 Parent(s): 98f938e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -35,6 +35,7 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.Q2_K.gguf) | Q2_K | 0.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* |
37
  | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended |
 
38
  | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.f16.gguf) | f16 | 3.8 | 16 bpw, overkill |
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
35
  | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.Q2_K.gguf) | Q2_K | 0.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* |
37
  | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Vakeel-8B-v2-mini-GGUF/resolve/main/Vakeel-8B-v2-mini.f16.gguf) | f16 | 3.8 | 16 bpw, overkill |
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant