MoE models recomended for 8GB of VRAM + MoE offloading
Patryk
WhiskyAKM
AI & ML interests
LLMs for low end hardware
Recent Activity
updated a collection 11 days ago
Low Vram + Offload NVFP4 2026.08 updated a model 11 days ago
WhiskyAKM/Nemotron-3.5-Lightning-30B-A3B-NVFP4-GGUF updated a collection 11 days ago
Low Vram + Offload 2026.08Organizations
models 21
WhiskyAKM/Nemotron-3.5-Lightning-30B-A3B-GGUF
Text Generation • 33B • Updated • 1.02k
WhiskyAKM/Nemotron-3.5-Lightning-30B-A3B-NVFP4-GGUF
Text Generation • 33B • Updated • 519
WhiskyAKM/Ling-3.0-flash-GGUF
Text Generation • 127B • Updated • 1.18k • 4
WhiskyAKM/Ling-3.0-Tiny-NVFP4-GGUF
Text Generation • 8B • Updated • 385
WhiskyAKM/Ling-3.0-Tiny-GGUF
Text Generation • 8B • Updated • 2.32k • 3
WhiskyAKM/Gemma-4-26B-A4B-it-qat-GGUF
Any-to-Any • 25B • Updated • 690
WhiskyAKM/Gemma-4-26B-A4B-it-qat-NVFP4-GGUF
Any-to-Any • 25B • Updated • 459
WhiskyAKM/Gemma-4-12B-it-qat-NVFP4-GGUF
Any-to-Any • 12B • Updated • 1.25k • 1
WhiskyAKM/LFM2.5-2.6B-NVFP4-GGUF
Text Generation • 3B • Updated • 373 • 3
WhiskyAKM/LFM2.5-2.6B-GGUF
Text Generation • 3B • Updated • 502
datasets 0
None public yet