Weight-only INT4 for RTX 3090/4090-class cards, where FP8 and NVFP4 are emulated or unusable. Full recipe on every card.
Alex Αdamopoulos
aleada
·
AI & ML interests
Finetuning, models quantization, agents, RAG, integration,
Recent Activity
updated a model 13 days ago
aleada/SmolLM3-3B-W4A16 updated a model 13 days ago
aleada/Pixtral-12B-W4A16 updated a model 13 days ago
aleada/Phi-4-mini-instruct-W4A16Organizations
None yet
models 8
aleada/SmolLM3-3B-W4A16
Text Generation • 3B • Updated • 333
aleada/Qwen3.6-27B-W4A16
Image-Text-to-Text • 28B • Updated • 76
aleada/Pixtral-12B-W4A16
Image-Text-to-Text • 13B • Updated • 89 • 1
aleada/Phi-4-mini-instruct-W4A16
Text Generation • 4B • Updated • 379
aleada/Phi-4-W4A16
Text Generation • 15B • Updated • 357
aleada/Llama-3.2-11B-Vision-Instruct-W4A16
Image-Text-to-Text • 11B • Updated • 119
aleada/Gemma-4-12B-it-W4A16
Image-Text-to-Text • 12B • Updated • 118
aleada/Gemma-3-12B-it-W4A16
Image-Text-to-Text • 12B • Updated • 38
datasets 0
None public yet