deucebucket/Qwen3.6-35B-A3B-Cerebellum-GGUF
Text Generation • 35B • Updated • 1.65k • 11
Fits 16 GB cards
Weights under ~14 GB so a 16 GB GPU runs them fully loaded with room for context. Measured footprints on each card.
-
-
deucebucket/Qwen3.6-35B-A3B-Heretic-Cerebellum-GGUF
Image-Text-to-Text • 35B • Updated • 4.7k • 7 -
deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF
Text Generation • 25B • Updated • 227 • 10 -
deucebucket/Gemma-4-26B-A4B-it-Heretic-Cerebellum-GGUF
Text Generation • 25B • Updated • 287 • 6 -
deucebucket/Qwen3.6-27B-Cerebellum-GGUF
Text Generation • 27B • Updated • 288 • 13 -
deucebucket/Qwen3.6-27B-Heretic-Cerebellum-GGUF
Image-Text-to-Text • 27B • Updated • 97 • 2 -
deucebucket/Qwen3.6-27B-Cerebellum-Q2K-GGUF
Text Generation • 27B • Updated • 5.65k • 2 -
deucebucket/Qwen3-14B-Cerebellum-GGUF
15B • Updated • 104 • 1 -
deucebucket/Qwen3-30B-A3B-Cerebellum-GGUF
31B • Updated • 113 • 2 -
deucebucket/Granite-4.1-30B-Cerebellum-GGUF
29B • Updated • 52 • 1 -
deucebucket/North-Mini-Code-Cerebellum-GGUF
Text Generation • 30B • Updated • 326 • 2
deucebucket/KAT-Coder-V2.5-Dev-Cerebellum-GGUF
Text Generation • 35B • Updated • 2.03k • 3Note 12.1 GB Qwen3.6-35B-A3B coding quant. 92.07% HumanEval+ chat base.