mradermacher commited on
Commit
9025fe4
1 Parent(s): 6507d07

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/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ1_S.gguf) | i1-IQ1_S | 25.7 | for the desperate |
30
- | [GGUF](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ1_M.gguf) | i1-IQ1_M | 27.8 | for the desperate |
31
  | [GGUF](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 32.2 | |
32
  | [GGUF](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 35.8 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ2_S.gguf) | i1-IQ2_S | 37.6 | |
@@ -41,7 +41,7 @@ more details, including on how to concatenate multi-part files.
41
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 58.2 | IQ3_S probably better |
42
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 63.4 | IQ3_M probably better |
43
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 64.6 | |
44
- | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ4_NL.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ4_NL.gguf.part2of2) | i1-IQ4_NL | 68.3 | slightly worse than Q4_K_S |
45
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 68.4 | fast, low quality |
46
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 68.7 | optimal size/speed/quality |
47
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 72.6 | fast, recommended |
@@ -49,7 +49,6 @@ more details, including on how to concatenate multi-part files.
49
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 85.4 | |
50
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 99.1 | 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/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ1_S.gguf) | i1-IQ1_S | 25.7 | for the desperate |
30
+ | [GGUF](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ1_M.gguf) | i1-IQ1_M | 27.8 | mostly desperate |
31
  | [GGUF](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 32.2 | |
32
  | [GGUF](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 35.8 | |
33
  | [GGUF](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ2_S.gguf) | i1-IQ2_S | 37.6 | |
 
41
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 58.2 | IQ3_S probably better |
42
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 63.4 | IQ3_M probably better |
43
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 64.6 | |
44
+ | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ4_NL.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-IQ4_NL.gguf.part2of2) | i1-IQ4_NL | 68.3 | prefer IQ4_XS |
45
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 68.4 | fast, low quality |
46
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 68.7 | optimal size/speed/quality |
47
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 72.6 | fast, recommended |
 
49
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 85.4 | |
50
  | [PART 1](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Bernstein-120b-i1-GGUF/resolve/main/Bernstein-120b.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 99.1 | 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