mradermacher commited on
Commit
cbbe516
1 Parent(s): 1542f5f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -26,7 +26,7 @@ more details, including on how to concatenate multi-part files.
26
  | Link | Type | Size/GB | Notes |
27
  |:-----|:-----|--------:|:------|
28
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 4.7 | for the desperate |
29
- | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 4.9 | for the desperate |
30
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 | |
31
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.3 | |
32
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 6.7 | |
@@ -40,7 +40,7 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.0 | IQ3_S probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.9 | IQ3_M probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.0 | |
43
- | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 11.6 | slightly worse than Q4_K_S |
44
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q4_0.gguf) | i1-Q4_0 | 11.6 | fast, low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.7 | optimal size/speed/quality |
46
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.3 | fast, recommended |
@@ -48,7 +48,6 @@ more details, including on how to concatenate multi-part files.
48
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.5 | |
49
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q6_K.gguf) | i1-Q6_K | 16.7 | practically like static Q6_K |
50
 
51
-
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):
54
 
 
26
  | Link | Type | Size/GB | Notes |
27
  |:-----|:-----|--------:|:------|
28
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 4.7 | for the desperate |
29
+ | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 4.9 | mostly desperate |
30
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 | |
31
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.3 | |
32
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 6.7 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.0 | IQ3_S probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.9 | IQ3_M probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.0 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 11.6 | prefer IQ4_XS |
44
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q4_0.gguf) | i1-Q4_0 | 11.6 | fast, low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.7 | optimal size/speed/quality |
46
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.3 | fast, recommended |
 
48
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.5 | |
49
  | [GGUF](https://huggingface.co/mradermacher/DaringMaid-20B-V1.1-i1-GGUF/resolve/main/DaringMaid-20B-V1.1.i1-Q6_K.gguf) | i1-Q6_K | 16.7 | practically like static Q6_K |
50
 
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
53