exllamav3 quantizations of zai-org/GLM-4.5-Air. Please note that support for this model is currently in the dev branch of exllamav3.
Some bigger quants to complement Turboderp's quants of this model and DoctorShotgun's 5.0bpw h6. GLM-4.5 (non-air) coming soon.
6.00 bpw h6 75.615 GiB
8.00 bpw h8 100.344 GiB
Model tree for MikeRoz/GLM-4.5-Air-exl3
Base model
zai-org/GLM-4.5-Air