mradermacher commited on
Commit
5d3d697
·
verified ·
1 Parent(s): 17f7f9f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -43,19 +43,27 @@ more details, including on how to concatenate multi-part files.
43
  | Link | Type | Size/GB | Notes |
44
  |:-----|:-----|--------:|:------|
45
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
46
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
47
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
49
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
 
52
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
54
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
56
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
 
57
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
58
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
 
 
 
59
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
43
  | Link | Type | Size/GB | Notes |
44
  |:-----|:-----|--------:|:------|
45
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
46
+ | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
47
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
48
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
51
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
52
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
54
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
56
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
57
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
58
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
59
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
60
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
62
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
63
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
64
+ | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
67
  | [GGUF](https://huggingface.co/mradermacher/UI-Ins-32B-i1-GGUF/resolve/main/UI-Ins-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
68
 
69
  Here is a handy graph by ikawrakow comparing some lower-quality quant