Hugging Face's logo

mradermacher
/
Dolphin-X1-Llama-3.1-405B-i1-GGUF

Transformers
GGUF
English
Model card Files
xet
Community
mradermacher commited on
Commit
0cf4262
·
verified ·
1 Parent(s): 05aa2af

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -40,6 +40,7 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own qwuants) |
41
  | [PART 1](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q2_K.gguf.part4of4) | i1-Q2_K | 149.4 | IQ3_XXS probably better |
42
  | [PART 1](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-IQ3_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-IQ3_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-IQ3_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-IQ3_M.gguf.part4of4) | i1-IQ3_M | 181.8 | |
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
 
40
  | [GGUF](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own qwuants) |
41
  | [PART 1](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q2_K.gguf.part4of4) | i1-Q2_K | 149.4 | IQ3_XXS probably better |
42
  | [PART 1](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-IQ3_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-IQ3_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-IQ3_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-IQ3_M.gguf.part4of4) | i1-IQ3_M | 181.8 | |
43
+ | [P1](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q4_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q4_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q4_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q4_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Dolphin-X1-Llama-3.1-405B-i1-GGUF/resolve/main/Dolphin-X1-Llama-3.1-405B.i1-Q4_K_S.gguf.part5of5) | i1-Q4_K_S | 230.6 | optimal size/speed/quality |
44
 
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant
46
  types (lower is better):