Hugging Face's logo

mradermacher
/
Meta-Llama-3.1-405B-Instruct-GGUF

Transformers
PyTorch
facebook
meta
llama
llama-3
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
800af78
•
1 Parent(s): f9ca987

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -34,6 +34,7 @@ more details, including on how to concatenate multi-part files.
34
  | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.IQ3_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.IQ3_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.IQ3_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.IQ3_S.gguf.part4of4) | IQ3_S | 177.7 | beats Q3_K* |
35
  | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_M.gguf.part4of4) | Q3_K_M | 197.6 | lower quality |
36
  | [P1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part5of5) | Q3_K_L | 215.3 | |
 
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
39
  types (lower is better):
 
34
  | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.IQ3_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.IQ3_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.IQ3_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.IQ3_S.gguf.part4of4) | IQ3_S | 177.7 | beats Q3_K* |
35
  | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_M.gguf.part4of4) | Q3_K_M | 197.6 | lower quality |
36
  | [P1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q3_K_L.gguf.part5of5) | Q3_K_L | 215.3 | |
37
+ | [P1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q4_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q4_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q4_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q4_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.Q4_K_S.gguf.part5of5) | Q4_K_S | 233.0 | fast, recommended |
38
 
39
  Here is a handy graph by ikawrakow comparing some lower-quality quant
40
  types (lower is better):