Malandrino PRO

Pier-Jean

·

AI & ML interests

Document parsing Quantization

Recent Activity

authored a paper 6 days ago

Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights

published an article 11 days ago

I put a 24 dimensional lattice in a CUDA kernel to run Qwen3-4B in 2.6 GB

updated a model 22 days ago

Pier-Jean/Qwen3-4B-LLVQ-2bit

View all activity

Organizations

liked a Space 5 months ago

Docling Studio

Generate and edit custom documents online

liked a model 12 months ago

ibm-granite/granite-docling-258M

Image-Text-to-Text • 0.3B • Updated Sep 23, 2025 • 210k • 1.26k

liked a model about 1 year ago

docling-project/SmolDocling-256M-preview

Image-Text-to-Text • 0.3B • Updated Sep 17, 2025 • 26.4k • 1.62k

liked a model over 1 year ago

cross-encoder/ms-marco-MiniLM-L6-v2

Text Ranking • 22.7M • Updated about 1 month ago • 86.8M • 315