mradermacher commited on
Commit
914c544
1 Parent(s): 7866b57

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -32,6 +32,7 @@ more details, including on how to concatenate multi-part files.
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
 
35
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.4 | mostly desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.0 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.6 | |
@@ -39,14 +40,18 @@ more details, including on how to concatenate multi-part files.
39
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ2_M.gguf) | i1-IQ2_M | 6.3 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q2_K.gguf) | i1-Q2_K | 6.9 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.2 | lower quality |
 
42
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.1 | IQ3_XS probably better |
 
43
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ3_M.gguf) | i1-IQ3_M | 8.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.0 | IQ3_S probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 9.7 | IQ3_M probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.0 | |
 
47
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 10.6 | optimal size/speed/quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 11.3 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 12.9 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q6_K.gguf) | i1-Q6_K | 15.3 | practically like static Q6_K |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ1_S.gguf) | i1-IQ1_S | 4.0 | for the desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.4 | mostly desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.0 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.6 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ2_M.gguf) | i1-IQ2_M | 6.3 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q2_K.gguf) | i1-Q2_K | 6.9 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.2 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 7.7 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.1 | IQ3_XS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ3_S.gguf) | i1-IQ3_S | 8.1 | beats Q3_K* |
46
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ3_M.gguf) | i1-IQ3_M | 8.3 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.0 | IQ3_S probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 9.7 | IQ3_M probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.0 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q4_0.gguf) | i1-Q4_0 | 10.6 | fast, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 10.6 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 11.3 | fast, recommended |
53
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 12.9 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 13.2 | |
55
  | [GGUF](https://huggingface.co/mradermacher/Solutus-3x7B-i1-GGUF/resolve/main/Solutus-3x7B.i1-Q6_K.gguf) | i1-Q6_K | 15.3 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant