Hugging Face's logo

mradermacher
/
Midnight-Miqu-103B-v1.0-GGUF

Transformers
GGUF
English
mergekit
Merge
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
158a112
•
1 Parent(s): f45fc33

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -32,7 +32,9 @@ more details, including on how to concatenate multi-part files.
32
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q4_K_S.gguf.part2of2) | Q4_K_S | 59.0 | fast, medium quality |
33
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q4_K_M.gguf.part2of2) | Q4_K_M | 62.3 | fast, medium quality |
34
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q5_K_S.gguf.part2of2) | Q5_K_S | 71.4 | |
 
35
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q6_K.gguf.part2of2) | Q6_K | 85.1 | very good quality |
 
36
 
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
32
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q4_K_S.gguf.part2of2) | Q4_K_S | 59.0 | fast, medium quality |
33
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q4_K_M.gguf.part2of2) | Q4_K_M | 62.3 | fast, medium quality |
34
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q5_K_S.gguf.part2of2) | Q5_K_S | 71.4 | |
35
+ | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q5_K_M.gguf.part2of2) | Q5_K_M | 73.3 | |
36
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q6_K.gguf.part2of2) | Q6_K | 85.1 | very good quality |
37
+ | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-GGUF/resolve/main/Midnight-Miqu-103B-v1.0.Q8_0.gguf.part3of3) | Q8_0 | 110.0 | fast, best quality |
38
 
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant