Hugging Face's logo

MikeRoz
/
Behemoth-R1-123B-v2-exl2

Text Generation
exllamav2
exl2
Model card Files
xet
 Community
MikeRoz commited on
Commit
b404ce4
·
verified ·
1 Parent(s): 76b7bff

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ exllamav2 quantizations of TheDrummer's [Behemoth-R1-123B-v2](https://huggingfac
12
 
13
  [2.50bpw h6](https://huggingface.co/MikeRoz/Behemoth-R1-123B-v2-exl2/tree/2.50bpw_H6) (Quantizing)
14
  [4.25bpw h6](https://huggingface.co/MikeRoz/Behemoth-R1-123B-v2-exl2/tree/4.25bpw_H6) (61.324 GiB)
15
- [8.00bpw h8](https://huggingface.co/MikeRoz/Behemoth-R1-123B-v2-exl2/tree/8.00bpw_H8) (114.559 GiB)
16
  [measurement.json](https://huggingface.co/MikeRoz/Behemoth-R1-123B-v2-exl2/resolve/main/measurement.json?download=true)
17
 
18
  The 4.25bpw quant will squeeze into 3 24GB GPUs with 16k fp16 context, but can load with more than 64k context in 4 24GB GPUs.
 
12
 
13
  [2.50bpw h6](https://huggingface.co/MikeRoz/Behemoth-R1-123B-v2-exl2/tree/2.50bpw_H6) (Quantizing)
14
  [4.25bpw h6](https://huggingface.co/MikeRoz/Behemoth-R1-123B-v2-exl2/tree/4.25bpw_H6) (61.324 GiB)
15
+ [8.00bpw h8](https://huggingface.co/MikeRoz/Behemoth-R1-123B-v2-exl2/tree/8.00bpw_H8) (114.559 GiB) (Uploading)
16
  [measurement.json](https://huggingface.co/MikeRoz/Behemoth-R1-123B-v2-exl2/resolve/main/measurement.json?download=true)
17
 
18
  The 4.25bpw quant will squeeze into 3 24GB GPUs with 16k fp16 context, but can load with more than 64k context in 4 24GB GPUs.