mradermacher commited on
Commit
bf6fb4f
1 Parent(s): 5d0339f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -27,7 +27,7 @@ more details, including on how to concatenate multi-part files.
27
  | Link | Type | Size/GB | Notes |
28
  |:-----|:-----|--------:|:------|
29
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ1_S.gguf) | i1-IQ1_S | 20.5 | for the desperate |
30
- | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ1_M.gguf) | i1-IQ1_M | 21.8 | for the desperate |
31
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 24.0 | |
32
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 26.0 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_S.gguf) | i1-IQ2_S | 27.6 | |
@@ -41,7 +41,7 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 39.3 | IQ3_S probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 42.6 | IQ3_M probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 42.8 | |
44
- | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ4_NL.gguf) | i1-IQ4_NL | 45.1 | slightly worse than Q4_K_S |
45
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_0.gguf) | i1-Q4_0 | 45.2 | fast, low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 45.3 | optimal size/speed/quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 47.8 | fast, recommended |
@@ -49,7 +49,6 @@ more details, including on how to concatenate multi-part files.
49
  | [PART 1](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 55.4 | |
50
  | [PART 1](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 63.4 | practically like static Q6_K |
51
 
52
-
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55
 
 
27
  | Link | Type | Size/GB | Notes |
28
  |:-----|:-----|--------:|:------|
29
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ1_S.gguf) | i1-IQ1_S | 20.5 | for the desperate |
30
+ | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ1_M.gguf) | i1-IQ1_M | 21.8 | mostly desperate |
31
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 24.0 | |
32
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 26.0 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ2_S.gguf) | i1-IQ2_S | 27.6 | |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 39.3 | IQ3_S probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 42.6 | IQ3_M probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 42.8 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-IQ4_NL.gguf) | i1-IQ4_NL | 45.1 | prefer IQ4_XS |
45
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_0.gguf) | i1-Q4_0 | 45.2 | fast, low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 45.3 | optimal size/speed/quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 47.8 | fast, recommended |
 
49
  | [PART 1](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 55.4 | |
50
  | [PART 1](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Rhea-72b-v0.5-i1-GGUF/resolve/main/Rhea-72b-v0.5.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 63.4 | practically like static Q6_K |
51
 
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):
54