Hugging Face's logo

mradermacher
/
Meta-Llama-3-70B-hf-GGUF

Transformers
GGUF
PyTorch
English
facebook
meta
llama
llama-3
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
023679b
·
verified ·
1 Parent(s): 4fed883

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -198,6 +198,7 @@ more details, including on how to concatenate multi-part files.
198
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
199
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
200
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
 
201
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
202
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
203
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
 
198
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
199
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
200
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
201
+ | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
202
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
203
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
204
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-hf-GGUF/resolve/main/Meta-Llama-3-70B-hf.Q5_K_S.gguf) | Q5_K_S | 48.8 | |