mradermacher commited on
Commit
010aaa4
1 Parent(s): a660ed3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -15,7 +15,7 @@ quantized_by: mradermacher
15
  static quants of https://huggingface.co/jukofyork/Dark-Miqu-70B
16
 
17
  <!-- provided-files -->
18
- 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.
19
  ## Usage
20
 
21
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -28,7 +28,19 @@ more details, including on how to concatenate multi-part files.
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
 
 
31
  | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
 
 
 
 
 
 
 
 
 
 
32
  | [PART 1](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
33
 
34
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
15
  static quants of https://huggingface.co/jukofyork/Dark-Miqu-70B
16
 
17
  <!-- provided-files -->
18
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dark-Miqu-70B-i1-GGUF
19
  ## Usage
20
 
21
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q2_K.gguf) | Q2_K | 25.6 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.IQ3_XS.gguf) | IQ3_XS | 28.4 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
34
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.IQ3_M.gguf) | IQ3_M | 31.0 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
43
+ | [PART 1](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
44
  | [PART 1](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dark-Miqu-70B-GGUF/resolve/main/Dark-Miqu-70B.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant