Hugging Face's logo

mradermacher
/
CodeLlama-70b-Instruct-hf-i1-GGUF

Transformers
GGUF
code
llama-2
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
de66872
·
verified ·
1 Parent(s): 0b95bb2

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -40,6 +40,7 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
45
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
 
40
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
44
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
46
  | [GGUF](https://huggingface.co/mradermacher/CodeLlama-70b-Instruct-hf-i1-GGUF/resolve/main/CodeLlama-70b-Instruct-hf.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |