Hugging Face's logo

mradermacher
/
miqu-1-103b-GGUF

Transformers
GGUF
mergekit
Merge
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
1f9bc10
•
1 Parent(s): ba4e96b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -2,6 +2,10 @@
2
  base_model: wolfram/miqu-1-103b
3
  language:
4
  - en
 
 
 
 
5
  library_name: transformers
6
  license: other
7
  quantized_by: mradermacher
@@ -36,14 +40,13 @@ more details, including on how to concatenate multi-part files.
36
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_L.gguf.part2of2) | Q3_K_L | 54.5 | |
37
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ4_XS.gguf.part2of2) | IQ4_XS | 56.0 | |
38
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_S.gguf.part2of2) | Q4_K_S | 59.0 | fast, recommended |
39
- | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ4_NL.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ4_NL.gguf.part2of2) | IQ4_NL | 59.1 | slightly worse than Q4_K_S |
40
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_M.gguf.part2of2) | Q4_K_M | 62.3 | fast, recommended |
41
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q5_K_S.gguf.part2of2) | Q5_K_S | 71.4 | |
42
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q5_K_M.gguf.part2of2) | Q5_K_M | 73.3 | |
43
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q6_K.gguf.part2of2) | Q6_K | 85.1 | very good quality |
44
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q8_0.gguf.part3of3) | Q8_0 | 110.0 | fast, best quality |
45
 
46
-
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
49
 
 
2
  base_model: wolfram/miqu-1-103b
3
  language:
4
  - en
5
+ - de
6
+ - fr
7
+ - es
8
+ - it
9
  library_name: transformers
10
  license: other
11
  quantized_by: mradermacher
 
40
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q3_K_L.gguf.part2of2) | Q3_K_L | 54.5 | |
41
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ4_XS.gguf.part2of2) | IQ4_XS | 56.0 | |
42
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_S.gguf.part2of2) | Q4_K_S | 59.0 | fast, recommended |
43
+ | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ4_NL.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.IQ4_NL.gguf.part2of2) | IQ4_NL | 59.1 | prefer IQ4_XS |
44
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q4_K_M.gguf.part2of2) | Q4_K_M | 62.3 | fast, recommended |
45
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q5_K_S.gguf.part2of2) | Q5_K_S | 71.4 | |
46
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q5_K_M.gguf.part2of2) | Q5_K_M | 73.3 | |
47
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q6_K.gguf.part2of2) | Q6_K | 85.1 | very good quality |
48
  | [PART 1](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/miqu-1-103b-GGUF/resolve/main/miqu-1-103b.Q8_0.gguf.part3of3) | Q8_0 | 110.0 | fast, best quality |
49
 
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):
52