mradermacher commited on
Commit
2c0e4e3
·
verified ·
1 Parent(s): 7244094

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -38,9 +38,11 @@ more details, including on how to concatenate multi-part files.
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own qwuants) |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate |
42
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.2 | |
 
44
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better |
@@ -50,8 +52,11 @@ more details, including on how to concatenate multi-part files.
50
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better |
52
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | |
 
53
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended |
 
 
55
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q6_K.gguf) | i1-Q6_K | 25.2 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own qwuants) |
41
+ | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ1_S.gguf) | i1-IQ1_S | 6.5 | for the desperate |
42
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate |
43
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ2_S.gguf) | i1-IQ2_S | 9.4 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better |
 
52
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better |
54
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q4_0.gguf) | i1-Q4_0 | 17.5 | fast, low quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality |
57
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended |
58
+ | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q5_K_M.gguf) | i1-Q5_K_M | 21.8 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Melinoe-30B-A3B-Thinking-i1-GGUF/resolve/main/Melinoe-30B-A3B-Thinking.i1-Q6_K.gguf) | i1-Q6_K | 25.2 | practically like static Q6_K |
61
 
62
  Here is a handy graph by ikawrakow comparing some lower-quality quant