mradermacher commited on
Commit
7f69b2a
1 Parent(s): 9cdacde

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -28,7 +28,7 @@ tags:
28
  static quants of https://huggingface.co/cognitivecomputations/dolphin-2.9.1-mixtral-1x22b
29
 
30
  <!-- provided-files -->
31
- 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.
32
  ## Usage
33
 
34
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -41,7 +41,19 @@ more details, including on how to concatenate multi-part files.
41
 
42
  | Link | Type | Size/GB | Notes |
43
  |:-----|:-----|--------:|:------|
 
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.IQ3_S.gguf) | IQ3_S | 9.8 | beats Q3_K* |
 
 
 
 
 
 
 
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q8_0.gguf) | Q8_0 | 23.7 | fast, best quality |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
28
  static quants of https://huggingface.co/cognitivecomputations/dolphin-2.9.1-mixtral-1x22b
29
 
30
  <!-- provided-files -->
31
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-i1-GGUF
32
  ## Usage
33
 
34
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
41
 
42
  | Link | Type | Size/GB | Notes |
43
  |:-----|:-----|--------:|:------|
44
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q2_K.gguf) | Q2_K | 8.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.IQ3_XS.gguf) | IQ3_XS | 9.3 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q3_K_S.gguf) | Q3_K_S | 9.7 | |
47
  | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.IQ3_S.gguf) | IQ3_S | 9.8 | beats Q3_K* |
48
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.IQ3_M.gguf) | IQ3_M | 10.2 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q3_K_M.gguf) | Q3_K_M | 10.9 | lower quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q3_K_L.gguf) | Q3_K_L | 11.8 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.IQ4_XS.gguf) | IQ4_XS | 12.1 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q4_K_S.gguf) | Q4_K_S | 12.8 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q4_K_M.gguf) | Q4_K_M | 13.4 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q5_K_S.gguf) | Q5_K_S | 15.4 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q5_K_M.gguf) | Q5_K_M | 15.8 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q6_K.gguf) | Q6_K | 18.3 | very good quality |
57
  | [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-mixtral-1x22b-GGUF/resolve/main/dolphin-2.9.1-mixtral-1x22b.Q8_0.gguf) | Q8_0 | 23.7 | fast, best quality |
58
 
59
  Here is a handy graph by ikawrakow comparing some lower-quality quant