24 GB cards and CPU offload Collection The big ones. Includes the 122B with its measured expert-offload recipe (about 18 GB VRAM plus 34 GB RAM). • 4 items • Updated 4 days ago
North-Mini-Code - Cerebellum Collection Coding-focused Cerebellum builds (per-group HumanEval ablation). • 2 items • Updated 4 days ago
Fits 16 GB cards Collection Weights under ~14 GB so a 16 GB GPU runs them fully loaded with room for context. Measured footprints on each card. • 12 items • Updated 4 days ago
deucebucket/KAT-Coder-V2.5-Dev-Cerebellum-GGUF Text Generation • 35B • Updated 4 days ago • 845 • 2
deucebucket/KAT-Coder-V2.5-Dev-Cerebellum-GGUF Text Generation • 35B • Updated 4 days ago • 845 • 2
deucebucket/KAT-Coder-V2.5-Dev-Cerebellum-GGUF Text Generation • 35B • Updated 4 days ago • 845 • 2