GGUF models by seeingterra
37 GGUF models quantized by seeingterra on Hugging Face. Sizes run from 14.8B to 23.6B parameters. The longest trained context is 128K tokens.
MA
Magistaroth 24B v1.1
Magistaroth · seeingterra
Params23.6B
Context128K
Smallest13.5 GB
MO
Morax 24B v1
Morax · seeingterra
Params23.6B
Context128K
Smallest25.1 GB
QW
NQLSG Qwen3 14B NovelFusion Cpt
Qwen · seeingterra
Params14.8B
Context40K
Smallest10.5 GB
QL
Qliphoth 24B v1.2
Qliphoth · seeingterra
Params23.6B
Context128K
Smallest25.1 GB
QL
Qliphoth 24B v1.2
Qliphoth · seeingterra
Params23.6B
Context128K
Smallest16.3 GB
ZE
Zepar 24B v1
Zepar · seeingterra
Params23.6B
Context128K
Smallest16.8 GB
QL
Qliphoth 24B v1.2
Qliphoth · seeingterra
Params23.6B
Context128K
Smallest16.8 GB
QL
Qliphoth 24B v1.2
Qliphoth · seeingterra
Params23.6B
Context128K
Smallest11.5 GB