Transformers
GGUF
English
Inference Endpoints
imatrix
conversational
mradermacher commited on
Commit
bc1beef
·
verified ·
1 Parent(s): 2bec4ee

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -42,6 +42,7 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
 
45
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
47
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
@@ -50,6 +51,7 @@ more details, including on how to concatenate multi-part files.
50
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
 
53
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
54
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
55
  | [PART 1](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
 
42
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* |
46
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
48
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
 
51
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
53
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q4_1.gguf) | i1-Q4_1 | 44.4 | |
55
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
56
  | [GGUF](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
57
  | [PART 1](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orca_mini_v8_1_70b-i1-GGUF/resolve/main/orca_mini_v8_1_70b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |