mradermacher commited on
Commit
9952fe5
·
verified ·
1 Parent(s): 22423dc

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -28,20 +28,26 @@ more details, including on how to concatenate multi-part files.
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
 
31
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ1_M.gguf) | i1-IQ1_M | 5.4 | mostly desperate |
32
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.1 | |
33
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.7 | |
 
34
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ2_M.gguf) | i1-IQ2_M | 7.7 | |
35
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q2_K.gguf) | i1-Q2_K | 8.4 | IQ3_XXS probably better |
36
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.7 | lower quality |
 
37
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.7 | IQ3_XS probably better |
 
38
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ3_M.gguf) | i1-IQ3_M | 10.2 | |
39
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.9 | IQ3_S probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.8 | IQ3_M probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.0 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.8 | optimal size/speed/quality |
43
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.4 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 15.4 | |
 
45
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q6_K.gguf) | i1-Q6_K | 18.4 | practically like static Q6_K |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ1_S.gguf) | i1-IQ1_S | 4.9 | for the desperate |
32
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ1_M.gguf) | i1-IQ1_M | 5.4 | mostly desperate |
33
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.1 | |
34
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.7 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ2_S.gguf) | i1-IQ2_S | 7.1 | |
36
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ2_M.gguf) | i1-IQ2_M | 7.7 | |
37
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q2_K.gguf) | i1-Q2_K | 8.4 | IQ3_XXS probably better |
38
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.7 | lower quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 9.3 | |
40
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.7 | IQ3_XS probably better |
41
+ | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ3_S.gguf) | i1-IQ3_S | 9.8 | beats Q3_K* |
42
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ3_M.gguf) | i1-IQ3_M | 10.2 | |
43
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.9 | IQ3_S probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.8 | IQ3_M probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.0 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q4_0.gguf) | i1-Q4_0 | 12.7 | fast, low quality |
47
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.8 | optimal size/speed/quality |
48
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.4 | fast, recommended |
49
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 15.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 15.8 | |
51
  | [GGUF](https://huggingface.co/mradermacher/MS-Moonlight-22B-v3-i1-GGUF/resolve/main/MS-Moonlight-22B-v3.i1-Q6_K.gguf) | i1-Q6_K | 18.4 | practically like static Q6_K |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant