deucebucket/Qwen3.5-122B-A10B-Cerebellum-GGUF
Text Generation • 122B • Updated • 71 • 5
24 GB cards and CPU offload
The big ones. Includes the 122B with its measured expert-offload recipe (about 18 GB VRAM plus 34 GB RAM).
-
-
deucebucket/Qwen3-32B-Cerebellum-GGUF
33B • Updated • 28 • 1 -
deucebucket/Granite-4.0-H-Small-Cerebellum-GGUF
Text Generation • 32B • Updated • 40 • 1
deucebucket/KAT-Coder-V2.5-Dev-Cerebellum-GGUF
Text Generation • 35B • Updated • 2.03k • 3Note KAT-Coder V2.5 Dev Cerebellum 14GB v2 (Qwen 3.6 35B-A3B)