gemma-4-31b-it-exl3 / README.md
turboderp's picture
Update README.md
6da09cb verified
|
Raw
History Blame Contribute Delete
1.83 kB
metadata
license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
base_model: google/gemma-4-31B-it
base_model_relation: quantized
quantized_by: turboderp
tags:
  - exl3

EXL3 quants of gemma-4-31B-it

mul1 quants (recommended, improved performance on exllamav3>=v1.0.0):

2.00 bits per weight
2.50 bits per weight
3.00 bits per weight
3.50 bits per weight
4.00 bits per weight
6.00 bits per weight

MCG quants (legacy):

2.00 bits per weight
2.25 bits per weight
2.50 bits per weight
3.00 bits per weight
3.50 bits per weight
4.00 bits per weight
5.00 bits per weight
6.00 bits per weight

kld