Hugging Face's logo

mradermacher
/
Llama-2-70b-hf-GGUF

Transformers
GGUF
PyTorch
English
facebook
meta
llama
llama-2
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
5941dc0
•
1 Parent(s): bedf8fa

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -27,7 +27,7 @@ tags:
27
  static quants of https://huggingface.co/NousResearch/Llama-2-70b-hf
28
 
29
  <!-- provided-files -->
30
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
31
  ## Usage
32
 
33
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -47,9 +47,11 @@ more details, including on how to concatenate multi-part files.
47
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.IQ3_M.gguf) | IQ3_M | 31.0 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
51
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
 
53
  | [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
54
  | [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
55
 
 
27
  static quants of https://huggingface.co/NousResearch/Llama-2-70b-hf
28
 
29
  <!-- provided-files -->
30
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF
31
  ## Usage
32
 
33
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
47
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.IQ3_M.gguf) | IQ3_M | 31.0 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
53
  | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
55
  | [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
56
  | [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF/resolve/main/Llama-2-70b-hf.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
57