mradermacher commited on
Commit
74fd37e
·
verified ·
1 Parent(s): 0e95332

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -38,10 +38,13 @@ more details, including on how to concatenate multi-part files.
38
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 56.4 | |
39
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 61.1 | IQ3_S probably better |
40
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 66.2 | IQ3_M probably better |
 
 
41
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 72.2 | optimal size/speed/quality |
42
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 76.5 | fast, recommended |
43
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 87.2 | |
44
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 89.7 | |
 
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
 
38
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 56.4 | |
39
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 61.1 | IQ3_S probably better |
40
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 66.2 | IQ3_M probably better |
41
+ | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 66.9 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 71.0 | fast, low quality |
43
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 72.2 | optimal size/speed/quality |
44
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 76.5 | fast, recommended |
45
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 87.2 | |
46
  | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 89.7 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 102.9 | practically like static Q6_K |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):