exllamav3 quantizations of TheDrummer's Behemoth-128B-V3
2.25bpw_h6 36.075 GiB
4.25bpw_h6 64.434 GiB (This model)
5.00bpw_h6 75.077 GiB
Tested without reasoning on Mistral v7 Tekken.
Model card WIP
exllamav3 quantizations of TheDrummer's Behemoth-128B-V3
2.25bpw_h6 36.075 GiB
4.25bpw_h6 64.434 GiB (This model)
5.00bpw_h6 75.077 GiB
Tested without reasoning on Mistral v7 Tekken.
Model card WIP
model-00001-of-00009.safetensors 8.5 GBmodel-00003-of-00009.safetensors 8.1 GBmodel-00004-of-00009.safetensors 8.1 GBmodel-00005-of-00009.safetensors 8.1 GBmodel-00006-of-00009.safetensors 8.1 GBmodel-00007-of-00009.safetensors 8.1 GBmodel-00008-of-00009.safetensors 8.1 GBmodel-00002-of-00009.safetensors 8.1 GBmodel-00009-of-00009.safetensors 4.2 GB有文件？提交种子。
提交种子