Hugging Face's logo

mradermacher
/
Mixtral-8x7B-Holodeck-v1-i1-GGUF

Transformers
GGUF
PyTorch
English
mixtral
fine-tuned
Mixture of Experts
Inference Endpoints
Model card Files Community
1
mradermacher commited on
Commit
5e8a298
•
1 Parent(s): 0412756

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -40,10 +40,10 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 21.7 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
43
- | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | almost as good as Q4_K_M |
44
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, medium quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.5 | |
46
- | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 | best weighted quant |
47
 
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
40
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 21.7 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, medium quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.5 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 | |
47
 
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant