Hugging Face's logo

mradermacher
/
mpt-30b-instruct-GGUF

Transformers
GGUF
English
Composer
MosaicML
llm-foundry
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b5ec72d
·
verified ·
1 Parent(s): 4525e54

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -49,6 +49,7 @@ more details, including on how to concatenate multi-part files.
49
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q3_K_S.gguf) | Q3_K_S | 13.1 | |
50
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.IQ3_M.gguf) | IQ3_M | 14.6 | |
51
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q3_K_M.gguf) | Q3_K_M | 15.8 | lower quality |
 
52
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q4_K_S.gguf) | Q4_K_S | 17.2 | fast, recommended |
53
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q3_K_L.gguf) | Q3_K_L | 17.3 | |
54
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q4_K_M.gguf) | Q4_K_M | 19.2 | fast, recommended |
 
49
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q3_K_S.gguf) | Q3_K_S | 13.1 | |
50
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.IQ3_M.gguf) | IQ3_M | 14.6 | |
51
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q3_K_M.gguf) | Q3_K_M | 15.8 | lower quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.IQ4_XS.gguf) | IQ4_XS | 16.3 | |
53
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q4_K_S.gguf) | Q4_K_S | 17.2 | fast, recommended |
54
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q3_K_L.gguf) | Q3_K_L | 17.3 | |
55
  | [GGUF](https://huggingface.co/mradermacher/mpt-30b-instruct-GGUF/resolve/main/mpt-30b-instruct.Q4_K_M.gguf) | Q4_K_M | 19.2 | fast, recommended |