Hugging Face's logo

mradermacher
/
kheops_compressed-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
llama
trl
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
81375aa
·
verified ·
1 Parent(s): 8d4ce2e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -38,6 +38,7 @@ more details, including on how to concatenate multi-part files.
38
  | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q2_K.gguf) | Q2_K | 0.2 | |
39
  | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.IQ3_S.gguf) | IQ3_S | 0.3 | beats Q3_K* |
40
  | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended |
 
41
  | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.f16.gguf) | f16 | 0.7 | 16 bpw, overkill |
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
38
  | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q2_K.gguf) | Q2_K | 0.2 | |
39
  | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.IQ3_S.gguf) | IQ3_S | 0.3 | beats Q3_K* |
40
  | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q8_0.gguf) | Q8_0 | 0.4 | fast, best quality |
42
  | [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.f16.gguf) | f16 | 0.7 | 16 bpw, overkill |
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant