MoE models recomended for 8GB of VRAM + MoE offloading
Patryk
WhiskyAKM
AI & ML interests
LLMs for low end hardware
Recent Activity
updated a model 1 day ago
WhiskyAKM/K2-Horizon-MoVA-36B-A4B-NVFP4-GGUF published a model 1 day ago
WhiskyAKM/K2-Horizon-MoVA-36B-A4B-NVFP4-GGUF updated a model 3 days ago
WhiskyAKM/K2-Horizon-0.9B-NVFP4-GGUFOrganizations
None yet
models 27
WhiskyAKM/K2-Horizon-MoVA-36B-A4B-NVFP4-GGUF
Text Generation • 37B • Updated • 288
WhiskyAKM/K2-Horizon-0.9B-NVFP4-GGUF
Text Generation • 1B • Updated • 116
WhiskyAKM/K2-Horizon-3.7B-NVFP4-GGUF
Text Generation • 5B • Updated • 259
WhiskyAKM/K2-Horizon-7B-NVFP4-GGUF
Text Generation • 9B • Updated • 260
WhiskyAKM/Gemma-4-12B-it-qat-NVFP4-GGUF
Any-to-Any • 12B • Updated • 954 • 1
WhiskyAKM/Gemma-4-E4B-it-qat-NVFP4-GGUF
Any-to-Any • 7B • Updated • 315 • 2
WhiskyAKM/Gemma-4-E2B-it-qat-NVFP4-GGUF
Any-to-Any • 5B • Updated • 151
WhiskyAKM/Spark-X2.5-4B-NVFP4-GGUF
Text Generation • 4B • Updated • 255
WhiskyAKM/Spark-X2.5-4B-GGUF
Text Generation • 4B • Updated • 382
WhiskyAKM/Gemma-4-E2B-it-qat-GGUF
Any-to-Any • 5B • Updated • 1.28k
datasets 0
None public yet