MoE models recomended for 8GB of VRAM + MoE offloading
Patryk
WhiskyAKM
AI & ML interests
LLMs for low end hardware
Recent Activity
updated a collection about 21 hours ago
Low Vram + Offload NVFP4 2026.08 updated a model about 21 hours ago
WhiskyAKM/Gemma-4-26B-A4B-it-qat-NVFP4-GGUF published a model about 21 hours ago
WhiskyAKM/Gemma-4-26B-A4B-it-qat-NVFP4-GGUFOrganizations
None yet
models 17
WhiskyAKM/Gemma-4-26B-A4B-it-qat-GGUF
Any-to-Any • 25B • Updated
WhiskyAKM/Gemma-4-26B-A4B-it-qat-NVFP4-GGUF
Any-to-Any • 25B • Updated
WhiskyAKM/Gemma-4-12B-it-qat-NVFP4-GGUF
Any-to-Any • 12B • Updated • 465
WhiskyAKM/LFM2.5-2.6B-NVFP4-GGUF
Text Generation • 3B • Updated
WhiskyAKM/LFM2.5-2.6B-GGUF
Text Generation • 3B • Updated
WhiskyAKM/Ling-3.0-flash-GGUF
Text Generation • 127B • Updated • 85 • 2
WhiskyAKM/G9v3-3B-GGUF
Text Generation • 3B • Updated • 790
WhiskyAKM/G9v3-3B-NVFP4-GGUF
Text Generation • 3B • Updated • 195
WhiskyAKM/Qwen3.6-35B-A3B-NVFP4-GGUF
Image-Text-to-Text • 36B • Updated • 395 • 1
WhiskyAKM/Qwen3.6-35B-A3B-GGUF
Image-Text-to-Text • 36B • Updated • 480
datasets 0
None public yet