mradermacher commited on
Commit
44a7c39
1 Parent(s): 20ac8bc

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -28,7 +28,7 @@ more details, including on how to concatenate multi-part files.
28
  | Link | Type | Size/GB | Notes |
29
  |:-----|:-----|--------:|:------|
30
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 15.0 | for the desperate |
31
- | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | for the desperate |
32
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 21.8 | |
@@ -42,7 +42,7 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 37.2 | |
45
- | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ4_NL.gguf) | i1-IQ4_NL | 39.4 | slightly worse than Q4_K_S |
46
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 39.4 | fast, low quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
@@ -50,7 +50,6 @@ more details, including on how to concatenate multi-part files.
50
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.2 | |
51
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | practically like static Q6_K |
52
 
53
-
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56
 
 
28
  | Link | Type | Size/GB | Notes |
29
  |:-----|:-----|--------:|:------|
30
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 15.0 | for the desperate |
31
+ | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | mostly desperate |
32
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 21.8 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 37.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ4_NL.gguf) | i1-IQ4_NL | 39.4 | prefer IQ4_XS |
46
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 39.4 | fast, low quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.2 | |
51
  | [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | practically like static Q6_K |
52
 
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55